{
  "notice": "bxzxxr MCP archive: a record of what public MCP servers declared when we listed them (we never call their tools). It is data, not a rating: nothing here says a server is safe, secure, verified or trustworthy, and a server can change after we looked. Secrets we detected are redacted; redacted tool lists are withheld and only their hash is shown.",
  "infrastructure": {
    "host": "v12dfs-production.up.railway.app",
    "site": "v12dfs-production.up.railway.app",
    "addresses": [
      {
        "address": "153.52.255.118",
        "endpoints": 10,
        "shared_infrastructure": false,
        "network": {
          "asn": 400940,
          "name": "RAILWAY - Railway",
          "prefix": "153.52.255.0/24",
          "country": "US"
        }
      }
    ],
    "addresses_recorded": true,
    "address_history": [
      {
        "addresses": [
          "153.52.255.118"
        ],
        "first_seen": "2026-11-21T14:33:00.907Z",
        "last_seen": "2026-11-21T14:33:00.907Z",
        "checks": 1
      }
    ],
    "hosting": [
      {
        "value": "Railway",
        "evidence": "host name ends in .up.railway.app"
      }
    ],
    "software": [],
    "server_info": {
      "name": "V12 DFS Optimizer",
      "version": "1.0.0",
      "protocol_version": "2025-06-18"
    },
    "headers": {
      "server": "railway-hikari"
    },
    "auth": null
  },
  "related": {
    "same_address": {
      "total": 9,
      "sample": [
        {
          "id": "138",
          "url": "https://agentberg.ai/mcp",
          "server_name": "ai.agentberg/agentberg",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:33:01.838Z"
        },
        {
          "id": "22533",
          "url": "https://mcp.crank.ing/mcp",
          "server_name": "ing.crank/crank",
          "last_state": "listed",
          "last_checked_at": "2026-11-21T13:15:07.794Z"
        },
        {
          "id": "22914",
          "url": "https://datascoop.io/mcp",
          "server_name": "io.datascoop/datascoop",
          "last_state": "listed",
          "last_checked_at": "2026-11-21T13:25:03.597Z"
        },
        {
          "id": "23113",
          "url": "https://mcp.opencomment.ai/mcp",
          "server_name": "io.github.02inf/opencomment-ai",
          "last_state": "listed",
          "last_checked_at": "2026-11-21T13:31:01.882Z"
        },
        {
          "id": "33593",
          "url": "https://mcp.sheetsdata.com/mcp",
          "server_name": "io.github.octoco-ltd/sheetsdata-mcp",
          "last_state": "listed",
          "last_checked_at": "2026-11-21T16:35:02.914Z"
        },
        {
          "id": "22848",
          "url": "https://clipwave.io/api/mcp",
          "server_name": "io.clipwave/clipwave",
          "last_state": "auth_required",
          "last_checked_at": "2026-11-21T13:23:04.573Z"
        },
        {
          "id": "22851",
          "url": "https://api.cloudlabels.io/mcp",
          "server_name": "io.cloudlabels/cloudlabels",
          "last_state": "auth_required",
          "last_checked_at": "2026-11-21T13:24:01.396Z"
        },
        {
          "id": "28241",
          "url": "https://udi.celltype.com/mcp",
          "server_name": "io.github.celltype/udi",
          "last_state": "auth_required",
          "last_checked_at": "2026-11-21T15:07:01.992Z"
        },
        {
          "id": "40283",
          "url": "https://scout-packs-production.up.railway.app/mcp",
          "server_name": "io.github.tigerops-win/scout-packs",
          "last_state": "error",
          "last_checked_at": "2026-11-21T18:07:00.921Z"
        }
      ]
    },
    "same_site": {
      "total": 0,
      "sample": []
    },
    "same_tool_list": {
      "total": 0,
      "sample": []
    },
    "same_publisher": {
      "publisher": "io.github.Jorgeperez0825",
      "total": 0,
      "sample": []
    },
    "same_repository": null,
    "note": "Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators."
  },
  "endpoint": {
    "id": "25227",
    "server_name": "io.github.Jorgeperez0825/v12-dfs",
    "url": "https://v12dfs-production.up.railway.app/mcp",
    "host": "v12dfs-production.up.railway.app",
    "transport": "streamable-http",
    "last_checked_at": "2026-11-21T14:33:00.907Z",
    "last_state": "listed",
    "last_detail": null,
    "consecutive_failures": 0,
    "current_sha": "0683da44c2a85457cf2c9465e041f22f5f798714b24ce8e6741ef1636027f30e",
    "first_listed_at": "2026-11-21T14:33:00.907Z",
    "created_at": "2026-11-21T08:30:10.104Z",
    "resolved_addresses": [
      "153.52.255.118"
    ]
  },
  "server": {
    "name": "io.github.Jorgeperez0825/v12-dfs",
    "title": null,
    "description": "AI-driven DFS lineup optimizer for MLB & NBA — build FanDuel & DraftKings lineups via MCP.",
    "version": "1.0.0",
    "registry_status": "active",
    "repository_url": null,
    "website_url": null,
    "published_at": "2026-06-17T06:17:19.980Z",
    "updated_at": "2026-06-17T06:17:19.980Z",
    "first_seen": "2026-11-21T08:30:09.616Z"
  },
  "other_endpoints": [],
  "intel": {
    "capabilities": [
      "runs-agents",
      "trades"
    ],
    "evm_addresses": [],
    "chains": [],
    "tokens": [],
    "computed_at": "2026-11-22T15:40:16.662Z"
  },
  "operator": null,
  "needs_sign_in": false,
  "reachability": {
    "window_days": 30,
    "checks": 1,
    "answered": 1,
    "answered_percent": 100,
    "avg_listing_latency_ms": 364,
    "first_check_in_window": "2026-11-21T14:33:00.907Z",
    "consecutive_failures_now": 0,
    "days": [
      {
        "day": "2026-11-21",
        "checks": 1,
        "answered": 1,
        "last_state": "listed"
      }
    ]
  },
  "tool_list": {
    "sha256": "0683da44c2a85457cf2c9465e041f22f5f798714b24ce8e6741ef1636027f30e",
    "tools": 35,
    "resources": 0,
    "prompts": 0,
    "first_seen": "2026-11-21T14:33:01.574Z",
    "tool_names": [
      "agent_guide",
      "health_check",
      "health_v12",
      "list_slates",
      "get_slate_players",
      "slate_health",
      "slate_refresh",
      "slate_diff",
      "list_presets",
      "generate_lineups",
      "run_mlb_postmortem",
      "list_contests",
      "list_live_contests",
      "contest_semaforo",
      "scout_field",
      "contest_advice",
      "fill_template",
      "late_swap",
      "admin_issue_key",
      "betting_agent_guide",
      "betting_player_form",
      "betting_analyze_prop",
      "betting_scan_edges",
      "betting_best_bets",
      "betting_build_parlay",
      "betting_log_bet",
      "betting_my_bets",
      "betting_settle_bet",
      "betting_cross_book",
      "betting_game_lines",
      "betting_market",
      "betting_sharp",
      "betting_game_model",
      "betting_matchup",
      "betting_market_movers"
    ],
    "declared": {
      "tools": [
        {
          "name": "agent_guide",
          "description": "Agent Guide\n\nSelf-serve onboarding: connect any agent (Claude/MCP or REST) to drive the\nV12 motor, the same engine the dashboard agent uses. No auth. Returns\ncopy-paste MCP + REST config with a PLACEHOLDER key, the endpoint map, and the\ngenerate body fields. Operators: issue each user their OWN key via\nPOST /v1/admin/create-key — never share one key.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json",
          "inputSchema": {
            "type": "object",
            "title": "agent_guideArguments",
            "properties": {}
          }
        },
        {
          "name": "health_check",
          "description": "Health\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"status\": \"Status\",\n  \"version\": \"Version\",\n  \"timestamp\": \"Timestamp\"\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "health_checkArguments",
            "properties": {}
          }
        },
        {
          "name": "health_v12",
          "description": "Health V12\n\nDeep health check for the V12 pipeline. Surfaces:\n  - last nightly regression run (pass/fail + per-slate deltas)\n  - regression baseline metadata\n  - recent preflight blockers (if any cached)\nNo auth required — monitoring endpoint.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json",
          "inputSchema": {
            "type": "object",
            "title": "health_v12Arguments",
            "properties": {}
          }
        },
        {
          "name": "list_slates",
          "description": "Get Slates\n\nList available V12 slates for today. Returns slate IDs, game counts, and lock times.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "list_slatesArguments",
            "properties": {
              "site": {
                "type": "string",
                "title": "site",
                "default": "fd"
              },
              "limit": {
                "type": "integer",
                "anyOf": [
                  {
                    "type": "integer"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "limit"
              },
              "sport": {
                "type": "string",
                "title": "sport",
                "default": "NBA"
              },
              "compact": {
                "type": "boolean",
                "title": "compact",
                "default": false
              },
              "playable": {
                "type": "boolean",
                "title": "playable",
                "default": false
              }
            }
          }
        },
        {
          "name": "get_slate_players",
          "description": "Get Slate Players Endpoint\n\nGet the V12 player pool for a specific slate ID.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "get_slate_playersArguments",
            "required": [
              "slate_id"
            ],
            "properties": {
              "limit": {
                "type": "integer",
                "anyOf": [
                  {
                    "type": "integer"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "limit"
              },
              "compact": {
                "type": "boolean",
                "title": "compact",
                "default": false
              },
              "slate_id": {
                "type": "integer",
                "title": "slate_id"
              }
            }
          }
        },
        {
          "name": "slate_health",
          "description": "Slate Health\n\nPre-flight diagnostic for a slate. Returns whether odds, projections,\nmatchup, and FD master-session are ready BEFORE the agent invokes\n/v1/generate.\n\nEither slate_id or date is required. When slate_id is given, the slate\nmetadata is also returned (games list, lock times). When only date is\ngiven, the data-pillar checks still run but game coverage cannot be\ncomputed (returned as null).\n\nREADING THE PROJECTION FRESHNESS (MLB especially): `stokastic.age_min` is the\nage of the cached snapshot FILE, NOT a data-quality signal. For MLB the cache\nis refreshed only twice a day, so mid-afternoon it routinely reads several\nhours old AND THAT IS FINE — a user-facing generate fetches projections LIVE\n(refresh_data=true), and `stokastic.generate_fetches_live=true` flags this.\nA stale `age_min` with a loaded, populated pool is NOT \"projections broken /\naces at 0 / no edge\": probable pitchers are set days ahead (non-zero), and\nonly confirmed BATTING lineups firm up ~1-2h before lock. Do NOT treat a stale\ncache age as a blocker or tell the user to wait/re-refresh — check the actual\npool (get_slate_players) for non-zero pitcher projections instead.\n\nBLOCKERS vs WARNINGS: a blocker means generation will not work (slate closed) or the slate has a\nPARTIAL odds gap (some games cached, some not). Nothing cached at all is a WARNING, not a blocker:\ngenerate fetches odds/projections live. `data_store_ok=false` / `degraded=true` means the cache\nstore could not be read: degraded service, builds still fetch live, do not report the data as\nunavailable and do not tell the user to wait.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "slate_healthArguments",
            "properties": {
              "date": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "date"
              },
              "site": {
                "type": "string",
                "title": "site",
                "default": "fd"
              },
              "sport": {
                "type": "string",
                "title": "sport",
                "default": "NBA"
              },
              "slate_id": {
                "type": "integer",
                "anyOf": [
                  {
                    "type": "integer"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "slate_id"
              },
              "include_snapshot": {
                "type": "boolean",
                "title": "include_snapshot",
                "default": false
              },
              "last_known_fingerprint": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "last_known_fingerprint"
              }
            }
          }
        },
        {
          "name": "slate_refresh",
          "description": "Slate Refresh\n\nRe-fetch projections + odds + slate metadata for a date.\n\nWrites to the configured store (Supabase in prod). Returns a summary\ndict (date, slate_id, n_games, n_players, n_upserted, n_odds, backend).\n\nAuth: requires X-API-Key OR X-Internal-Secret (cron use). This is a\nwrite op that costs one Stokastic + one ESPN API call.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "slate_refreshArguments",
            "properties": {
              "date": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "date"
              },
              "site": {
                "type": "string",
                "title": "site",
                "default": "FD"
              },
              "sport": {
                "type": "string",
                "title": "sport",
                "default": "NBA"
              }
            }
          }
        },
        {
          "name": "slate_diff",
          "description": "Slate Diff\n\nCompute what changed since a previously-stored snapshot.\n\nBody shape:\n  {\n    \"slate_id\": 32867,\n    \"date\": \"2026-05-11\",\n    \"sport\": \"NBA\",\n    \"site\": \"FD\",\n    \"previous\": {\n      \"v\": \"v1\",\n      \"players\": [{\"id\",\"name\",\"status\",\"salary\",\"proj\"}, ...],\n      \"odds\":    [{\"game\",\"ou\",\"spread\",\"home_ml\",\"away_ml\"}, ...]\n    }\n  }\n\nReturns a structured diff: which players changed status / salary /\nprojection, which games moved spread or O/U, which players were added\nor removed from the pool. The thresholds for \"changed\":\n  - status: any non-empty difference (Q→OUT, ''→OUT, GTD→IN, etc.)\n  - salary: any integer delta\n  - projection: |delta| >= 0.5 fantasy points\n  - odds spread: |delta| >= 0.5\n  - odds ou: |delta| >= 0.5\n  - odds ml: |delta| >= 10 (American odds noise floor)\n\nNo auth required — read-only computation off in-memory current snapshot\nplus the caller-supplied previous one.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "slate_diffArguments",
            "properties": {}
          }
        },
        {
          "name": "list_presets",
          "description": "Get Presets\n\nList the available strategy presets (gpp_pro_pattern, gpp_sniper, gpp_balanced, gpp_volume, cash_grinder, gpp_contrarian, gpp_mass_entry) with their configurations. No auth required.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "list_presetsArguments",
            "properties": {
              "sport": {
                "type": "string",
                "title": "sport",
                "default": "nba"
              }
            }
          }
        },
        {
          "name": "generate_lineups",
          "description": "Generate Lineups\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"status\": \"Status\",\n  \"generated_at\": \"Generated At\",\n  \"warnings\": [],\n  \"exposures\": {},\n  \"lineups\": []\n}\n```\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "generate_lineupsArguments",
            "required": [
              "date"
            ],
            "properties": {
              "date": {
                "type": "string",
                "title": "date",
                "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
                "description": "Slate date YYYY-MM-DD"
              },
              "runs": {
                "type": "integer",
                "title": "runs",
                "default": 5,
                "maximum": 10,
                "minimum": 1,
                "description": "Accepted for tier limits and response metadata. Portfolio quality is controlled by preset, candidate_pool_size, pool_oversample_multiplier, and simulation settings."
              },
              "seed": {
                "type": "integer",
                "title": "seed",
                "default": 42,
                "maximum": 999999,
                "minimum": 0,
                "description": "Random seed for reproducibility"
              },
              "locks": {
                "type": "array",
                "items": {},
                "title": "locks",
                "default": [],
                "maxItems": 15,
                "description": "Players to lock in"
              },
              "sport": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string",
                    "pattern": "^(nba|mlb|nfl|NBA|MLB|NFL)$"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "sport",
                "default": "nba",
                "description": "Sport engine to run: nba, mlb or nfl."
              },
              "style": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string",
                    "pattern": "^(aggressive|balanced|safe)$"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "style"
              },
              "avoids": {
                "type": "array",
                "items": {},
                "title": "avoids",
                "default": [],
                "maxItems": 100,
                "description": "Players to avoid"
              },
              "n_sims": {
                "type": "integer",
                "anyOf": [
                  {
                    "type": "integer",
                    "maximum": 100000,
                    "minimum": 100
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "n_sims",
                "description": "Monte Carlo iterations when simulation is enabled."
              },
              "preset": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "preset",
                "default": "gpp_pro_pattern",
                "description": "Strategy preset key. OMIT it to get the engine default per sport (NBA FanDuel: gpp_pure_score, whose #1 lineup is the exact projection optimum; MLB: gpp_pro_structure). The listed default is a legacy placeholder; send a preset only when the user asks for one."
              },
              "lineups": {
                "type": "integer",
                "anyOf": [
                  {
                    "type": "integer",
                    "maximum": 150,
                    "minimum": 1
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "lineups",
                "description": "Number of lineups (overrides preset default)"
              },
              "platform": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string",
                    "pattern": "^(fd|dk|fanduel|draftkings)$"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "platform",
                "default": "fd",
                "description": "V12 platform profile: fd or dk."
              },
              "sim_mode": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string",
                    "pattern": "^(off|mvn|on)$"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "sim_mode",
                "description": "Simulation mode. NBA: mvn/off. MLB: on/off."
              },
              "slate_id": {
                "type": "integer",
                "anyOf": [
                  {
                    "type": "integer"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "slate_id",
                "description": "Specific slate ID from /v1/slates. Overrides date-based lookup."
              },
              "strategy": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string",
                    "pattern": "^(gpp|cash)$"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "strategy",
                "description": "GPP or cash game strategy"
              },
              "plan_only": {
                "type": "boolean",
                "title": "plan_only",
                "default": false,
                "description": "When true, the server resolves preset / contest / authoritative slate / top-run-env / locks but does NOT run the optimizer. Returns a Plan response so the user can review and confirm before spending credits on a real generate. Costs 0 credits; normal slate-open safety checks still apply."
              },
              "contest_id": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string",
                    "maxLength": 80
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "contest_id",
                "description": "Optional contest handle for building an entry-update CSV from the user's existing contest entries."
              },
              "fd_user_id": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string",
                    "pattern": "^\\d+$",
                    "maxLength": 32
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "fd_user_id",
                "description": "DEPRECATED on /v1/generate: fd_user_id is bound server-side to your API key (see /v1/admin/bind-fd-user). Body value is IGNORED on the public route unless X-Internal-Secret matches. Kept on the schema for the internal admin path only."
              },
              "focus_games": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "title": "focus_games",
                "default": [],
                "maxItems": 30,
                "description": "Game keys to emphasize, e.g. ['PHI@BOS']. Applies a small documented projection nudge."
              },
              "allow_locked": {
                "type": "boolean",
                "title": "allow_locked",
                "default": false,
                "description": "Explicit REPLAY override: rebuilds EVERY slot from scratch, ignoring which players are already locked. Default false blocks slate_id generation once any game has started. To edit existing FanDuel NBA entries after lock use POST /v1/late-swap (late_swap) instead."
              },
              "refresh_data": {
                "type": "boolean",
                "title": "refresh_data",
                "default": true,
                "description": "Force a fresh V12 data refresh for user-facing generation. Backtests should set false."
              },
              "exposure_caps": {
                "type": "object",
                "title": "exposure_caps",
                "default": {},
                "description": "Per-player exposure caps {name: 0.0-1.0}",
                "additionalProperties": true
              },
              "contest_fallback": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string",
                    "pattern": "^(slate_only)$"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "contest_fallback",
                "description": "Escape hatch when a contest_id cannot be mapped to a slate (contest_slate_unresolved). 'slate_only' + an explicit slate_id builds on THAT slate and skips contest-specific behavior (field-size routing, entry-template mapping) instead of failing the whole generate. Requires slate_id; without it the request still fails closed. Omit for normal contest-anchored builds."
              },
              "contest_field_size": {
                "type": "integer",
                "anyOf": [
                  {
                    "type": "integer",
                    "minimum": 1
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "contest_field_size",
                "description": "Total entries (field size) of the selected contest. Governs the MLB objective: field <= 10 -> max-mean (mlb_small_field_se); field > 10 -> ceiling (mlb_se_ceiling) with a continuous ceiling tilt and the real field size fed into contest simulation. A matched contest_id lobby row is authoritative; this value is the fallback when that row is unavailable."
              },
              "entry_template_csv": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string",
                    "maxLength": 4000000
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "entry_template_csv",
                "description": "Raw CSV of a FanDuel entries-upload-template the operator already downloaded. When present, the entry-upload is filled from its OWN entry_ids locally — no FanDuel API / session / PerimeterX call. Fixes fd_entry_template_auth_expired when the user already has the template in hand."
              },
              "team_exposure_caps": {
                "type": "object",
                "anyOf": [
                  {
                    "type": "array",
                    "items": {
                      "type": "array",
                      "maxItems": 2,
                      "minItems": 2,
                      "prefixItems": [
                        {
                          "type": "string"
                        },
                        {
                          "type": "number"
                        }
                      ]
                    }
                  },
                  {
                    "type": "object",
                    "additionalProperties": {
                      "type": "number"
                    }
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "team_exposure_caps",
                "description": "Per-team portfolio caps, as [[\"COL\",0.5],...] pairs or {\"COL\":0.5} dict."
              },
              "candidate_pool_size": {
                "type": "integer",
                "anyOf": [
                  {
                    "type": "integer",
                    "maximum": 5000,
                    "minimum": 0
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "candidate_pool_size",
                "description": "Exact candidate pool size for Pool→Rank→Keep-N selection. NBA FanDuel: omit it on a single-lineup request without exposure floors and the server uses a pool of 100 (the dashboard default); every other request keeps the preset's own pool (pool = lineups, or the preset's multiplier such as gpp_volume's 2x) unless you set this or pool_oversample_multiplier; cash and gpp_mass_entry never get the default; 0 means the preset multiplier only. MLB: 0/omitted uses the preset multiplier. DraftKings REST ignores these knobs."
              },
              "contest_max_entries": {
                "type": "integer",
                "anyOf": [
                  {
                    "type": "integer",
                    "maximum": 150,
                    "minimum": 1
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "contest_max_entries",
                "description": "Max entries per user for the selected contest. Used to identify multi-entry mass GPPs (>=4) which keep the caller's preset. Field SIZE, not this, governs the MLB objective — see contest_field_size."
              },
              "max_hitter_exposure": {
                "type": "number",
                "anyOf": [
                  {
                    "type": "number",
                    "maximum": 1,
                    "exclusiveMinimum": 0
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "max_hitter_exposure",
                "description": "Portfolio cap: max share of delivered lineups any ONE hitter may appear in (0.4 = 40%). Pitchers exempt."
              },
              "max_pitcher_exposure": {
                "type": "number",
                "anyOf": [
                  {
                    "type": "number",
                    "maximum": 1,
                    "exclusiveMinimum": 0
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "max_pitcher_exposure",
                "description": "Portfolio cap: max share of delivered lineups any ONE pitcher may appear in."
              },
              "projection_overrides": {
                "type": "array",
                "items": {
                  "type": "object",
                  "additionalProperties": true
                },
                "title": "projection_overrides",
                "default": [],
                "maxItems": 2000,
                "description": "User-uploaded projection/ownership rows. Supports name/player_id/team/position/projection/ownership/ceiling/floor/stddev."
              },
              "auto_team_exposure_cap": {
                "type": "number",
                "anyOf": [
                  {
                    "type": "number",
                    "maximum": 1,
                    "exclusiveMinimum": 0
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "auto_team_exposure_cap",
                "description": "Default per-team portfolio cap (share of lineups containing ANY given team). Per-team entries in team_exposure_caps win over it."
              },
              "pool_oversample_multiplier": {
                "type": "number",
                "anyOf": [
                  {
                    "type": "number",
                    "maximum": 10,
                    "minimum": 1
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "pool_oversample_multiplier",
                "description": "Candidate pool multiplier when candidate_pool_size is not set. NBA FanDuel: setting it replaces the single-lineup default pool."
              }
            }
          }
        },
        {
          "name": "run_mlb_postmortem",
          "description": "Run Mlb Postmortem\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"status\": \"Status\",\n  \"generated_at\": \"Generated At\",\n  \"date\": \"Date\",\n  \"game_id\": \"Game Id\",\n  \"entries\": 1,\n  \"field_lineups\": 1,\n  \"training_rows\": 1,\n  \"missing_sources\": [\n    \"string\"\n  ],\n  \"results\": {},\n  \"history_validation\": {},\n  \"field\": {},\n  \"diagnostics\": {},\n  \"simulator_feed\": {},\n  \"warnings\": [\n    \"string\"\n  ]\n}\n```\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "run_mlb_postmortemArguments",
            "required": [
              "date",
              "game_id",
              "history_csv"
            ],
            "properties": {
              "date": {
                "type": "string",
                "title": "date",
                "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
                "description": "Slate date YYYY-MM-DD"
              },
              "game_id": {
                "type": "string",
                "title": "game_id",
                "maxLength": 32,
                "minLength": 3,
                "description": "V12 slate/game handle, e.g. 129715."
              },
              "history_csv": {
                "type": "string",
                "title": "history_csv",
                "minLength": 1,
                "description": "Raw FanDuel contest-history CSV content."
              },
              "upload_csvs": {
                "type": "array",
                "items": {
                  "type": "object",
                  "title": "PostmortemUploadCsv",
                  "required": [
                    "content"
                  ],
                  "properties": {
                    "content": {
                      "type": "string",
                      "title": "Content",
                      "minLength": 1,
                      "description": "Raw FanDuel upload/template CSV content."
                    },
                    "filename": {
                      "type": "string",
                      "title": "Filename",
                      "default": "upload.csv",
                      "maxLength": 240
                    }
                  }
                },
                "title": "upload_csvs",
                "default": [],
                "maxItems": 20
              },
              "sabersim_csv": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "sabersim_csv",
                "description": "Optional external lineup export for comparison."
              },
              "sync_supabase": {
                "type": "boolean",
                "title": "sync_supabase",
                "default": true,
                "description": "Upsert simulator training rows to production store when configured."
              },
              "top_field_rank": {
                "type": "integer",
                "title": "top_field_rank",
                "default": 200,
                "maximum": 1000,
                "minimum": 1
              },
              "history_filename": {
                "type": "string",
                "title": "history_filename",
                "default": "contest-history.csv",
                "maxLength": 240
              }
            }
          }
        },
        {
          "name": "list_contests",
          "description": "Contest Registry\n\nList contest strategy registry entries for agents and the dashboard.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "list_contestsArguments",
            "properties": {
              "sport": {
                "type": "string",
                "title": "sport",
                "default": "MLB"
              },
              "platform": {
                "type": "string",
                "title": "platform",
                "default": "fd"
              }
            }
          }
        },
        {
          "name": "list_live_contests",
          "description": "Live Contests\n\nReturn latest V12 contest context without backend identifiers.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "list_live_contestsArguments",
            "properties": {
              "limit": {
                "type": "integer",
                "anyOf": [
                  {
                    "type": "integer"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "limit",
                "default": 250
              },
              "sport": {
                "type": "string",
                "title": "sport",
                "default": "MLB"
              },
              "compact": {
                "type": "boolean",
                "title": "compact",
                "default": true
              },
              "platform": {
                "type": "string",
                "title": "platform",
                "default": "fd"
              }
            }
          }
        },
        {
          "name": "contest_semaforo",
          "description": "Contest Semaforo\n\nVIP-only: per-contest play/skip verdict from the owner's verified P&L\nbands + structure gates + rake/fill math. See core/data/contest_semaforo.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "contest_semaforoArguments",
            "properties": {
              "limit": {
                "type": "integer",
                "anyOf": [
                  {
                    "type": "integer"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "limit",
                "default": 60
              },
              "sport": {
                "type": "string",
                "title": "sport",
                "default": "MLB"
              },
              "platform": {
                "type": "string",
                "title": "platform",
                "default": "fd"
              }
            }
          }
        },
        {
          "name": "scout_field",
          "description": "Scout Field\n\nVIP-only (owner order 8/16): opponent-scouting profiles for the small\nsingle-entry band. The owner's $65 table runs the SAME regulars nightly;\nthis returns each regular's fingerprint — days seen, avg score,\nchalkiness (overlap with field consensus), favorite pitchers/bats and\nhead-to-head vs the owner — built from harvested full fields\n(brain/scout_profiles.json, refreshed by the local scouting pipeline;\npackaged snapshot as fallback so the endpoint never 500s on a fresh\nvolume). Same fail-closed allowlist as the semaforo.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "scout_fieldArguments",
            "properties": {
              "contest": {
                "type": "string",
                "title": "contest",
                "default": "Knuckleball"
              },
              "min_days": {
                "type": "integer",
                "title": "min_days",
                "default": 3
              }
            }
          }
        },
        {
          "name": "contest_advice",
          "description": "Contest Advice\n\nAdvice for a concrete contest name. Resolves the name against the LIVE\nlobby FIRST so a real live contest is never reported missing (the curated\nregistry is only a subset — that was the \"$800 Wed MLB Home Run no existe\"\nbug), then layers registry strategy advice on top when a template matches.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "contest_adviceArguments",
            "required": [
              "name"
            ],
            "properties": {
              "name": {
                "type": "string",
                "title": "name"
              },
              "sport": {
                "type": "string",
                "title": "sport",
                "default": "MLB"
              },
              "platform": {
                "type": "string",
                "title": "platform",
                "default": "fd"
              }
            }
          }
        },
        {
          "name": "fill_template",
          "description": "Fill Template\n\nFill a downloaded FanDuel/DK entries-template with already-generated\nlineups WITHOUT re-running the optimizer — the MCP-callable equivalent of the\ndashboard's fill_template. Keeps each entry row's leading columns (entry_id,\ncontest_id, fee) and replaces the roster-slot columns with a lineup's upload\ntokens, cycling lineups if there are more entry rows than lineups.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "fill_templateArguments",
            "required": [
              "template_csv",
              "lineups"
            ],
            "properties": {
              "lineups": {
                "type": "array",
                "items": {
                  "type": "array",
                  "items": {
                    "type": "string"
                  }
                },
                "title": "lineups",
                "maxItems": 200,
                "description": "Each lineup = upload tokens in template roster-slot order."
              },
              "template_csv": {
                "type": "string",
                "title": "template_csv",
                "maxLength": 8000000,
                "description": "Raw CSV of the entries-template (headers + entry rows)."
              },
              "lineup_header": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string",
                    "maxLength": 200
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "lineup_header",
                "description": "The `upload.csv_header` the lineups came with (e.g. 'PG,SG,SF,PF,C,G/F,F/C,UTIL,UTIL'). When given, the template is filled only if its roster columns are exactly these; without it a FanDuel NBA flex template (G/F, F/C columns) is refused because the order of the tokens is unknown."
              }
            }
          }
        },
        {
          "name": "late_swap",
          "description": "Late Swap Entries\n\nFanDuel NBA late swap: re-solve the OPEN slots of your existing entries; locked players stay in their slot.\n\nSend the FanDuel entries CSV for the slate (after the first tip: the 'Edit entries' download; before lock:\nthe entries-upload template). A player whose game has started keeps his exact column; every other slot is\nre-solved on fresh projections and OUT news with the salary cap and 4-per-team rule over the WHOLE lineup.\nReturns the same file with only those cells changed (`csv`, upload it at FanDuel > Edit entries) and a\nper-entry diff. Started slates are hidden by list_slates(playable=true); pass the slate_id from\nlist_slates(playable=false), or omit it to use the FanDuel fixture id inside the file. NBA FanDuel classic only.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"status\": \"Status\",\n  \"csv\": \"Csv\",\n  \"filename\": \"Filename\",\n  \"slate_id\": 1,\n  \"fd_slate_id\": \"Fd Slate Id\",\n  \"date\": \"Date\",\n  \"salary_cap\": 1,\n  \"layout\": \"Layout\",\n  \"mode\": \"Mode\",\n  \"lock_buffer_minutes\": 1,\n  \"entries_total\": 1,\n  \"entries_changed\": 1,\n  \"entries_unchanged\": 1,\n  \"entries_infeasible\": 1,\n  \"per_entry\": [\n    {\n      \"entry_id\": \"Entry Id\",\n      \"contest_id\": \"Contest Id\",\n      \"contest_name\": \"Contest Name\",\n      \"status\": \"Status\",\n      \"reason\": \"Reason\",\n      \"locked\": [\n        {\n          \"col\": 1,\n          \"label\": \"Label\",\n          \"player_id\": \"Player Id\",\n          \"name\": \"Name\"\n        }\n      ],\n      \"swaps\": [\n        {\n          \"col\": 1,\n          \"label\": \"Label\",\n          \"in_id\": \"In Id\",\n          \"in_name\": \"In Name\"\n        }\n      ],\n      \"proj_before\": 1.0,\n      \"gain\": 1.0\n    }\n  ],\n  \"started_games\": [\n    \"string\"\n  ],\n  \"closing_games\": [\n    \"string\"\n  ],\n  \"open_games\": [\n    \"string\"\n  ],\n  \"evaluated_at_utc\": \"Evaluated At Utc\",\n  \"solves\": 1,\n  \"warnings\": [\n    \"string\"\n  ],\n  \"note\": \"Note\"\n}\n```\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "late_swapArguments",
            "required": [
              "template_csv"
            ],
            "properties": {
              "date": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string",
                    "pattern": "^\\d{4}-\\d{2}-\\d{2}$"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "date",
                "description": "Slate date YYYY-MM-DD. Default: today in America/New_York."
              },
              "mode": {
                "enum": [
                  "optimal",
                  "replace_out"
                ],
                "type": "string",
                "title": "mode",
                "default": "optimal",
                "description": "'optimal' re-solves every open slot (an entry is edited only when it gains >= min_gain projected points, or holds an OUT/missing player); 'replace_out' replaces only open-slot players who are OUT, have no projection, or are avoided."
              },
              "sport": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string",
                    "maxLength": 20
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "sport",
                "default": "nba",
                "description": "Only 'nba' is supported."
              },
              "avoids": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "title": "avoids",
                "maxItems": 100,
                "description": "Player names or ids never brought into an open slot. An avoided player already in an open slot is swapped out (both modes) unless his game starts within lock_buffer_minutes; a locked player is never removed."
              },
              "min_gain": {
                "type": "number",
                "title": "min_gain",
                "default": 0.5,
                "maximum": 50,
                "minimum": 0,
                "description": "Projected points a healthy, valid entry must gain before it is edited (mode 'optimal' only)."
              },
              "platform": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string",
                    "maxLength": 20
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "platform",
                "default": "fd",
                "description": "Only 'fd' (FanDuel) is supported."
              },
              "slate_id": {
                "type": "integer",
                "anyOf": [
                  {
                    "type": "integer",
                    "minimum": 1
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "slate_id",
                "description": "V12 slate_id from /v1/slates, or the FanDuel fixture id (the prefix of every player/contest id in the file, e.g. 135843). Omit it to use the fixture id read from the template's contest_id."
              },
              "template_csv": {
                "type": "string",
                "title": "template_csv",
                "maxLength": 8000000,
                "minLength": 1,
                "description": "Raw CSV of the FanDuel entries file for the slate: the 'Edit entries' download after lock, or the entries-upload template before lock. Rows keep their entry_id; the returned CSV is this file with only the open roster cells of entry rows changed."
              },
              "lock_buffer_minutes": {
                "type": "integer",
                "title": "lock_buffer_minutes",
                "default": 4,
                "maximum": 30,
                "minimum": 0,
                "description": "A game starting within this many minutes takes no incoming player (the upload may land after its lock)."
              }
            }
          }
        },
        {
          "name": "admin_issue_key",
          "description": "Issue Key\n\nIdempotently issue a user's API key and ALWAYS return the paste-able\nconnect block. Returns the email's existing active key (or mints one) so a\nuser keeps a single key across dashboard reloads; with rotate=true, revokes\nthe existing keys and mints a fresh one. Admin-gated — the dashboard's\nper-user provision route (which verifies the user's Firebase token) calls\nthis server-side, never the browser.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"api_key\": \"Api Key\",\n  \"tier\": \"Tier\",\n  \"limits\": {}\n}\n```\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "admin_issue_keyArguments",
            "required": [
              "email"
            ],
            "properties": {
              "tier": {
                "type": "string",
                "title": "tier",
                "default": "personal",
                "pattern": "^(starter|personal|business)$"
              },
              "email": {
                "type": "string",
                "title": "email",
                "maxLength": 200,
                "minLength": 5
              },
              "rotate": {
                "type": "boolean",
                "title": "rotate",
                "default": false,
                "description": "Revoke existing keys and mint a fresh one."
              }
            }
          }
        },
        {
          "name": "betting_agent_guide",
          "description": "Betting Agent Guide\n\nHow any agent uses the MLB betting tools + how to read the output.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json",
          "inputSchema": {
            "type": "object",
            "title": "betting_agent_guideArguments",
            "properties": {}
          }
        },
        {
          "name": "betting_player_form",
          "description": "Player Form\n\nStreak / splits / recent form for any player ('racha de X').\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_player_formArguments",
            "required": [
              "name"
            ],
            "properties": {
              "name": {
                "type": "string",
                "title": "name"
              },
              "season": {
                "type": "integer",
                "title": "season",
                "default": 2026
              }
            }
          }
        },
        {
          "name": "betting_analyze_prop",
          "description": "Analyze Prop\n\nModel a single player's prop vs tonight's FanDuel line -> edge.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_analyze_propArguments",
            "required": [
              "name"
            ],
            "properties": {
              "name": {
                "type": "string",
                "title": "name"
              },
              "prop": {
                "type": "string",
                "title": "prop",
                "default": "home_run"
              },
              "season": {
                "type": "integer",
                "title": "season",
                "default": 2026
              },
              "threshold": {
                "type": "integer",
                "title": "threshold",
                "default": 2
              }
            }
          }
        },
        {
          "name": "betting_scan_edges",
          "description": "Scan Edges\n\nTonight's prop board ranked by model edge (VALUE first).\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_scan_edgesArguments",
            "properties": {
              "prop": {
                "type": "string",
                "title": "prop",
                "default": "home_run"
              },
              "coors": {
                "type": "boolean",
                "title": "coors",
                "default": false
              },
              "limit": {
                "type": "integer",
                "title": "limit",
                "default": 15
              },
              "season": {
                "type": "integer",
                "title": "season",
                "default": 2026
              },
              "min_edge": {
                "type": "number",
                "title": "min_edge",
                "default": 2
              },
              "threshold": {
                "type": "integer",
                "title": "threshold",
                "default": 2
              }
            }
          }
        },
        {
          "name": "betting_best_bets",
          "description": "Best Bets\n\nTHE board sweep — scans EVERY main prop market (HR/RBI/hit/total_bases/\n2+hits/stolen_base) in one call and returns the top edges across all of them,\nnot just home runs. Power props carry the Savant validation (CONFIRMED power\nranked above neutral/noise). Use this for an open 'what's hot / best plays /\nwhat do you recommend tonight' so you NEVER conclude off a single-market scan.\nA SCREEN vs the vig line — validate with CLV; game-side value is separate\n(betting_sharp / betting_game_model).\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_best_betsArguments",
            "properties": {
              "limit": {
                "type": "integer",
                "title": "limit",
                "default": 12
              },
              "min_edge": {
                "type": "number",
                "title": "min_edge",
                "default": 2
              }
            }
          }
        },
        {
          "name": "betting_build_parlay",
          "description": "Build Parlay\n\nDeterministic parlay analysis for BOTH leg shapes. Body:\n{legs:[...], ticket_odds?}. PROP legs {name, prop, threshold} keep the\nlegacy correlation-aware EV. GAME-side legs (ML / run line / total / team\ntotal / F5, selected by the `market` field) — the slips users actually\npaste — are priced from the CURRENT de-vigged market at that exact market/\nline (canonical team resolution), falling back to the market-anchored run\nmodel for totals; per-leg fair prob + edge vs the slip's price, combined\npayout / breakeven / fair prob / EV under a documented independence\nassumption. Legs sharing a game are flagged correlated=true and get a\ncorrelation_warning INSTEAD of a combined edge. ticket_odds (the slip's\nprinted combined price) is verified vs the leg product — >2% off flags\nticket_odds_mismatch (the slip was misread; do not trust the numbers).\nNEVER estimate a parlay in prose — this endpoint is the math.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_build_parlayArguments",
            "required": [
              "legs"
            ],
            "properties": {
              "legs": {
                "type": "array",
                "items": {
                  "type": "object",
                  "title": "_ParlayLeg",
                  "properties": {
                    "line": {
                      "anyOf": [
                        {
                          "type": "number"
                        },
                        {
                          "type": "null"
                        }
                      ],
                      "title": "Line"
                    },
                    "name": {
                      "anyOf": [
                        {
                          "type": "string"
                        },
                        {
                          "type": "null"
                        }
                      ],
                      "title": "Name"
                    },
                    "prop": {
                      "type": "string",
                      "title": "Prop",
                      "default": "home_run"
                    },
                    "side": {
                      "anyOf": [
                        {
                          "type": "string"
                        },
                        {
                          "type": "null"
                        }
                      ],
                      "title": "Side"
                    },
                    "team": {
                      "anyOf": [
                        {
                          "type": "string"
                        },
                        {
                          "type": "null"
                        }
                      ],
                      "title": "Team"
                    },
                    "market": {
                      "anyOf": [
                        {
                          "type": "string"
                        },
                        {
                          "type": "null"
                        }
                      ],
                      "title": "Market"
                    },
                    "threshold": {
                      "type": "integer",
                      "title": "Threshold",
                      "default": 2
                    },
                    "american_odds": {
                      "anyOf": [
                        {
                          "type": "integer"
                        },
                        {
                          "type": "null"
                        }
                      ],
                      "title": "American Odds"
                    }
                  },
                  "description": "One parlay leg — TWO shapes, discriminated by the `market` field.\n\nPROP leg (legacy):   {name, prop, threshold?}\nGAME-side leg (C12): {market: moneyline|run_line|total|team_total|\n                      f5_moneyline|f5_total, team, side: over/under/home/\n                      away/<team>, line?, american_odds (the SLIP's price —\n                      authoritative for the payout math)}."
                },
                "title": "legs"
              },
              "ticket_odds": {
                "type": "integer",
                "anyOf": [
                  {
                    "type": "integer"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "ticket_odds"
              }
            }
          }
        },
        {
          "name": "betting_log_bet",
          "description": "Log Bet\n\nRecord a bet you placed (per user) so we can track P&L + CLV over time.\nBody: {uid, market, selection, odds (American), stake, line?, prop?, team?,\ngame?, book?}. Append-only — this is the evidence base that PROVES edge.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_log_betArguments",
            "required": [
              "uid",
              "market",
              "selection",
              "odds",
              "stake"
            ],
            "properties": {
              "uid": {
                "type": "string",
                "title": "uid"
              },
              "book": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "book"
              },
              "game": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "game"
              },
              "line": {
                "type": "number",
                "anyOf": [
                  {
                    "type": "number"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "line"
              },
              "odds": {
                "type": "integer",
                "title": "odds"
              },
              "prop": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "prop"
              },
              "team": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "team"
              },
              "stake": {
                "type": "number",
                "title": "stake"
              },
              "market": {
                "type": "string",
                "title": "market"
              },
              "selection": {
                "type": "string",
                "title": "selection"
              }
            }
          }
        },
        {
          "name": "betting_my_bets",
          "description": "My Bets\n\nA user's bet history + P&L / CLV summary. avg_clv_pct > 0 over time = you're\nbeating the closing line = real edge (the only durable proof).\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_my_betsArguments",
            "required": [
              "uid"
            ],
            "properties": {
              "uid": {
                "type": "string",
                "title": "uid"
              }
            }
          }
        },
        {
          "name": "betting_settle_bet",
          "description": "Settle Bet\n\nSettle a logged bet. Body: {uid, bet_id, result: won|lost|push,\nclosing_odds?}. closing_odds lets us compute CLV (did you beat the close).\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_settle_betArguments",
            "required": [
              "uid",
              "bet_id",
              "result"
            ],
            "properties": {
              "uid": {
                "type": "string",
                "title": "uid"
              },
              "bet_id": {
                "type": "string",
                "title": "bet_id"
              },
              "result": {
                "type": "string",
                "title": "result"
              },
              "closing_odds": {
                "type": "integer",
                "anyOf": [
                  {
                    "type": "integer"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "closing_odds"
              }
            }
          }
        },
        {
          "name": "betting_cross_book",
          "description": "Cross Book\n\nCross-book value: FanDuel vs DraftKings (DK pulled via ESPN's public API,\nno key/WS). LINE_SHOP (the books hang different numbers — take the easier\nside) and PRICE_SHOP (better price, same line) are CONFIRMED edges, no model\nneeded. Arbitrage is NOT auto-reported (needs over/under sides, which ESPN\ndoesn't label). Overnight only pitcher_strikeouts overlaps; richer markets\nappear near game time.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_cross_bookArguments",
            "properties": {
              "prop": {
                "type": "string",
                "title": "prop",
                "default": "pitcher_strikeouts"
              }
            }
          }
        },
        {
          "name": "betting_game_lines",
          "description": "Game Lines\n\nGAME markets — moneyline / run total / run line for today's MLB games. This\nanswers the 'quién gana / cuántas carreras / pronóstico Yankees vs Toronto'\nquestions that player props CAN'T (V12 used to just refuse them). Optional\nteam filter ('Yankees', 'NYY'). MARKET data from ESPN's public scoreboard,\nsurfaced as-is — V12 has NO game-outcome model, so this is the book's own\nnumber, never a fabricated prediction. A book may not have posted a game yet\n(fields null) — say so, don't invent a line.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_game_linesArguments",
            "properties": {
              "date": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "date"
              },
              "team": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "team"
              }
            }
          }
        },
        {
          "name": "betting_market",
          "description": "Market\n\nFULL FanDuel market board for a team's game — EVERY market with real odds +\nde-vig fair price, so NO market question goes unanswered. Game lines (ML /\ntotal / run line), FIRST 5 INNINGS (F5), TEAM TOTALS, NRFI/YRFI, alternate\nlines, AND the full player-prop menu (HR / 2+ HR / hit / 2+ hits / RBI /\n2+ RBI / run / single / double / triple / total bases / stolen base / K).\nThe book's market surfaced as-is (no model). For our model edge on a prop,\nfollow up with betting_analyze_prop.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_marketArguments",
            "required": [
              "team"
            ],
            "properties": {
              "date": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "date"
              },
              "team": {
                "type": "string",
                "title": "team"
              }
            }
          }
        },
        {
          "name": "betting_sharp",
          "description": "Sharp\n\nSHARP value — FanDuel vs PINNACLE (the sharpest book, ~2% hold). Pinnacle's\nde-vigged line ≈ TRUE probability, so this is the most reliable value signal in\nthe kit, NO model needed: edge_vs_sharp = FD's price minus the sharp's true\nprob; POSITIVE means FanDuel pays MORE than fair (real value vs the market).\nPlus total line-shop. Pinnacle only lists UPCOMING games (gone once started).\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_sharpArguments",
            "required": [
              "team"
            ],
            "properties": {
              "date": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "date"
              },
              "team": {
                "type": "string",
                "title": "team"
              }
            }
          }
        },
        {
          "name": "betting_game_model",
          "description": "Game Model\n\nMODEL the GAME run markets — TEAM TOTALS (over/under) and NRFI/YRFI — vs\nthe FanDuel line, MARKET-ANCHORED: expected_runs = the book's de-vigged\nimplied mean + 0.25×(structural model − book), and every edge is computed vs\nthe FAIR (de-vigged) probability, never the raw vig price. The structural\ninputs (season runs/game, opposing STARTER + BULLPEN run factors, park;\nnegative-binomial tails) supply only the tilt. Entries with anchored=false /\nmodel_only=true carry edge=null — present them as context, NEVER as value.\nA SCREEN vs the market, not a lock — validate with CLV. For raw lines on\nevery market use betting_market.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_game_modelArguments",
            "required": [
              "team"
            ],
            "properties": {
              "date": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "date"
              },
              "team": {
                "type": "string",
                "title": "team"
              }
            }
          }
        },
        {
          "name": "betting_matchup",
          "description": "Matchup\n\nGROUNDING — the real game for a team today: probable pitchers + the POSTED\nlineup (ACTUAL player names from MLB statsapi) + the market line + the CONTEXT\na pro reasons with: home-plate UMPIRE (strike zone → totals/Ks), the INJURY\nreport (who's OUT / Day-To-Day), and BULLPEN health (ERA / blown saves). Call\nthis BEFORE naming any player or discussing a game. Name ONLY the players this\nreturns — never a roster from memory (that is how the agent ends up naming\nplayers who aren't on the team).\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_matchupArguments",
            "required": [
              "team"
            ],
            "properties": {
              "date": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "date"
              },
              "team": {
                "type": "string",
                "title": "team"
              }
            }
          }
        },
        {
          "name": "betting_market_movers",
          "description": "Market Movers\n\nMARKET pattern (not model opinion): how FanDuel lines MOVED today, from the\ncaptured snapshots. A line that shortened = money coming in (sharp/news); a\ndrift = money off. This is the 'obvious opportunity' signal — market-confirmed,\nindependent of our unproven model. Needs accumulated capture; thin → thin.\n\n### Responses:\n\n**200**: Successful Response (Success Response)\nContent-Type: application/json\n**422**: Validation Error\nContent-Type: application/json\n\n**Example Response:**\n```json\n{\n  \"detail\": [\n    {\n      \"loc\": [],\n      \"msg\": \"Message\",\n      \"type\": \"Error Type\",\n      \"ctx\": {}\n    }\n  ]\n}\n```",
          "inputSchema": {
            "type": "object",
            "title": "betting_market_moversArguments",
            "properties": {
              "date": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "date"
              },
              "prop": {
                "type": "string",
                "anyOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "null"
                  }
                ],
                "title": "prop"
              },
              "min_move": {
                "type": "number",
                "title": "min_move",
                "default": 3
              }
            }
          }
        }
      ],
      "tools_omitted": 0,
      "resources": [],
      "prompts": []
    },
    "instructions": "DFS workflow: (1) list_slates(playable=true) -> pick slate_id. (2) slate_health(slate_id, sport) BEFORE generate_lineups — a slate-locked blocker is a hard stop; 'odds/projections not cached' is only a WARNING (generate fetches them live; call slate_refresh first for the freshest data and the latest confirmations). (3) Resolve the contest: contest_advice(name) -> live_match.contest_id, or list_contests / list_live_contests. Pass a UNIQUE contest_id, never a name: if contest_advice returns ambiguous:true (same name on >1 slate), pick from alternatives by slate_id/start_time. (4) generate_lineups(date, sport, slate_id, contest_id, preset, lineups) — pass entry_template_csv (your downloaded FanDuel entries-template) for an upload-ready CSV; WITHOUT it you get a review-only roster CSV that FanDuel rejects with '0 entries updated'. (5) After lock (FanDuel NBA): call late_swap(template_csv=<the contest's FanDuel 'Edit entries' CSV>, slate_id) — players whose game started stay in their exact slot and only open slots are re-solved; upload the returned csv before next_lock_et. list_slates(playable=true) HIDES started slates: use list_slates(playable=false) or omit slate_id (the FanDuel fixture id in the CSV is used). On a started slate the slate-locked blocker stops generate_lineups, not late_swap; never use allow_locked=true or fill_template to edit started entries (both overwrite locked players). Pass X-API-Key on heavy tools."
  },
  "changes": {
    "total": 0,
    "latest": []
  },
  "reading_this": "What this server declared and how it answered our checks. Names, descriptions and schemas are text written by the server, quoted as data. Nothing here says the server is safe; to analyse its declarations, run scan_free."
}