{
  "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": "agentstack.tech",
    "site": "agentstack.tech",
    "addresses": [
      {
        "address": "173.249.44.53",
        "endpoints": 1,
        "shared_infrastructure": false,
        "network": {
          "asn": 51167,
          "name": "CONTABO - Contabo GmbH",
          "prefix": "173.249.44.0/23",
          "country": "DE"
        }
      }
    ],
    "addresses_recorded": true,
    "address_history": [
      {
        "addresses": [
          "173.249.44.53"
        ],
        "first_seen": "2026-11-21T14:45:01.138Z",
        "last_seen": "2026-11-21T14:45:01.138Z",
        "checks": 1
      }
    ],
    "hosting": [],
    "software": [
      {
        "value": "nginx",
        "evidence": "Server header \"nginx/1.31.9\""
      }
    ],
    "server_info": {
      "name": "agentstack",
      "version": "0.4.27",
      "protocol_version": "2025-06-18"
    },
    "headers": {
      "server": "nginx/1.31.9",
      "strict-transport-security": "max-age=31536000; includeSubDomains",
      "access-control-allow-origin": "*, *"
    },
    "auth": null
  },
  "related": {
    "same_address": {
      "total": 0,
      "sample": []
    },
    "same_site": {
      "total": 0,
      "sample": []
    },
    "same_tool_list": {
      "total": 0,
      "sample": []
    },
    "same_publisher": {
      "publisher": "io.github.agentstacktech",
      "total": 0,
      "sample": []
    },
    "same_repository": {
      "repository_url": "https://github.com/agentstacktech/AgentStack",
      "total": 0,
      "sample": []
    },
    "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": "27260",
    "server_name": "io.github.agentstacktech/agentstack",
    "url": "https://agentstack.tech/mcp",
    "host": "agentstack.tech",
    "transport": "streamable-http",
    "last_checked_at": "2026-11-21T14:45:01.138Z",
    "last_state": "listed",
    "last_detail": null,
    "consecutive_failures": 0,
    "current_sha": "0f9446294a074c631834d2a8f1caaefe70f9be0080930d13171038821adb3444",
    "first_listed_at": "2026-11-21T14:45:01.138Z",
    "created_at": "2026-11-21T09:10:03.450Z",
    "resolved_addresses": [
      "173.249.44.53"
    ]
  },
  "server": {
    "name": "io.github.agentstacktech/agentstack",
    "title": "AgentStack (agentstack.tech)",
    "description": "Backend for AI agents: one batched tool over ~668 actions (hosting, storage, auth, payments).",
    "version": "1.0.0",
    "registry_status": "active",
    "repository_url": "https://github.com/agentstacktech/AgentStack",
    "website_url": "https://agentstack.tech",
    "published_at": "2026-10-06T07:36:21.611Z",
    "updated_at": "2026-10-06T07:36:21.611Z",
    "first_seen": "2026-11-21T09:05:06.672Z"
  },
  "other_endpoints": [],
  "intel": {
    "capabilities": [],
    "evm_addresses": [],
    "chains": [],
    "tokens": [],
    "computed_at": "2026-11-22T15:41:13.767Z"
  },
  "operator": null,
  "needs_sign_in": false,
  "reachability": {
    "window_days": 30,
    "checks": 1,
    "answered": 1,
    "answered_percent": 100,
    "avg_listing_latency_ms": 1408,
    "first_check_in_window": "2026-11-21T14:45:01.138Z",
    "consecutive_failures_now": 0,
    "days": [
      {
        "day": "2026-11-21",
        "checks": 1,
        "answered": 1,
        "last_state": "listed"
      }
    ]
  },
  "tool_list": {
    "sha256": "0f9446294a074c631834d2a8f1caaefe70f9be0080930d13171038821adb3444",
    "tools": 2,
    "resources": 4,
    "prompts": 74,
    "first_seen": "2026-11-21T14:45:02.549Z",
    "tool_names": [
      "agentstack.execute",
      "agentstack.read"
    ],
    "declared": {
      "tools": [
        {
          "name": "agentstack.execute",
          "title": "AgentStack execute",
          "description": "AUTH-FIRST: auth.get_profile before mutate. IDE: Connect; no auth.login in chat. Unauth: auth_choices; skip work_next. Mutate: OAuth/PAT (mcp:execute). Anon: bootstrap_ack+create_project_anonymous. Spine: plan_get->work_next->plan_claim->plan_execute. WG: work_next->plan_claim->plan_execute; follow packet.next_action. Prompts: session_setup, execute_budget.",
          "inputSchema": {
            "type": "object",
            "required": [
              "steps"
            ],
            "properties": {
              "steps": {
                "type": "array",
                "items": {
                  "type": "object",
                  "required": [
                    "id",
                    "action"
                  ],
                  "properties": {
                    "id": {
                      "type": "string",
                      "description": "Step id in batch."
                    },
                    "action": {
                      "type": "string",
                      "description": "Dotted action from /mcp/actions."
                    },
                    "params": {
                      "type": "object",
                      "description": "Action params."
                    }
                  },
                  "description": "One catalog action."
                },
                "minItems": 1,
                "description": "Steps; one heavy LLM per sync execute."
              },
              "context": {
                "type": "object",
                "properties": {
                  "project_id": {
                    "type": "integer",
                    "description": "Tenant project id."
                  }
                },
                "description": "session.v1; project_id required."
              },
              "options": {
                "type": "object",
                "properties": {
                  "goal": {
                    "type": "string",
                    "description": "Binds the batch to a playbook. A direct call uses execution_intent direct and omits goal. Per-step query must match this text."
                  },
                  "async": {
                    "type": "boolean",
                    "description": "Queue; poll discovery.job_status."
                  },
                  "envelope": {
                    "enum": [
                      "compact",
                      "full"
                    ],
                    "type": "string",
                    "description": "compact (default) | full — ADR MCP_EXECUTE_ENVELOPE_COMPACT_V2"
                  },
                  "recipe_id": {
                    "type": "string",
                    "description": "MCP recipe id."
                  },
                  "stopOnError": {
                    "type": "boolean",
                    "description": "Stop on first failure."
                  },
                  "focus_node_id": {
                    "type": "string",
                    "description": "Work graph node id from agents.work_next packet."
                  },
                  "continueOnError": {
                    "type": "boolean",
                    "description": "Continue after failure."
                  },
                  "idempotency_key": {
                    "type": "string",
                    "description": "Retry receipt key."
                  },
                  "semantic_strict": {
                    "type": "boolean",
                    "description": "Reject batch_semantic_anchor_conflict when anchor set."
                  },
                  "execution_intent": {
                    "enum": [
                      "direct",
                      "workflow",
                      "validate"
                    ],
                    "type": "string",
                    "description": "Batch lane: direct, workflow, or validate."
                  },
                  "plan_execute_mode": {
                    "type": "boolean",
                    "description": "Bind plan_execute lane for graph mutations."
                  }
                },
                "description": "batch.v1 controls."
              }
            },
            "description": "batch.v1 execute. Direct call: options.execution_intent=direct and no goal. {action, params} is accepted and becomes one step. goal binds a playbook."
          },
          "outputSchema": {
            "type": "object",
            "properties": {
              "ok": {
                "type": "boolean",
                "description": "False on total failure."
              },
              "job_id": {
                "type": "string",
                "description": "Poll id."
              },
              "timings": {
                "type": "object",
                "description": "Batch phase ms (hydrate_ms, preflight_ms, …).",
                "additionalProperties": {
                  "type": "number"
                }
              },
              "agent_os": {
                "type": "object",
                "description": "Follow next_step."
              },
              "recovery": {
                "type": "object",
                "description": "Next action when blocked."
              },
              "trace_id": {
                "type": "string",
                "description": "Support trace."
              },
              "error_code": {
                "type": "string",
                "description": "Stable failure code."
              },
              "execution_mode": {
                "type": "string",
                "description": "async when queued."
              },
              "response_bytes": {
                "type": "integer",
                "description": "Approximate serialized JSON size of the batch root."
              },
              "partial_success": {
                "type": "boolean",
                "description": "Some steps failed."
              }
            },
            "description": "result.v1 batch envelope."
          },
          "annotations": {
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": false,
            "destructiveHint": false
          }
        },
        {
          "name": "agentstack.read",
          "title": "AgentStack read",
          "description": "Read-only batch (effect read/evaluate). Same {steps, context, options} body as agentstack.execute. Server rejects mutate steps.",
          "inputSchema": {
            "type": "object",
            "required": [
              "steps"
            ],
            "properties": {
              "steps": {
                "type": "array",
                "items": {
                  "type": "object",
                  "required": [
                    "id",
                    "action"
                  ],
                  "properties": {
                    "id": {
                      "type": "string",
                      "description": "Step id."
                    },
                    "action": {
                      "type": "string",
                      "description": "Dotted action."
                    },
                    "params": {
                      "type": "object",
                      "description": "Action params."
                    }
                  },
                  "description": "One catalog action.",
                  "additionalProperties": true
                },
                "minItems": 1,
                "description": "Same items as agentstack.execute."
              },
              "context": {
                "type": "object",
                "properties": {
                  "project_id": {
                    "type": "integer",
                    "description": "Tenant project id."
                  }
                },
                "description": "session.v1.",
                "additionalProperties": true
              },
              "options": {
                "type": "object",
                "description": "Same keys as agentstack.execute options.",
                "additionalProperties": true
              }
            },
            "description": "Same body as agentstack.execute. Writes rejected.",
            "additionalProperties": true
          },
          "outputSchema": {
            "type": "object",
            "properties": {
              "ok": {
                "type": "boolean",
                "description": "False on total failure."
              },
              "trace_id": {
                "type": "string",
                "description": "Support trace."
              },
              "error_code": {
                "type": "string",
                "description": "Stable failure code."
              },
              "partial_success": {
                "type": "boolean",
                "description": "Some steps failed."
              }
            },
            "description": "Same result.v1 envelope as agentstack.execute."
          },
          "annotations": {
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        }
      ],
      "tools_omitted": 0,
      "resources": [
        {
          "name": "Platform planes",
          "uri": "agentstack://planes",
          "mimeType": "text/plain",
          "description": "Project config, storage, hosting, knowledge, CRM, agents, bots, integrations, logic, generation, release"
        },
        {
          "name": "MCP catalog summary",
          "uri": "agentstack://catalog/summary",
          "mimeType": "application/json",
          "description": "Lightweight action totals, catalog etag, registry dimensions"
        },
        {
          "name": "Session setup ladder",
          "uri": "agentstack://instructions/session",
          "mimeType": "text/markdown",
          "description": "Mandatory auth → project → context.project_id order (instruction plane SoT)"
        },
        {
          "name": "Work graph ladder",
          "uri": "agentstack://instructions/work-graph",
          "mimeType": "text/plain",
          "description": "Closed-loop plan graph spine — work_next before catalog shopping"
        }
      ],
      "prompts": [
        {
          "name": "create_logic_rule",
          "description": "Create a backend logic rule from natural language description",
          "arguments": [
            {
              "name": "description",
              "required": true,
              "description": "Natural language description of what the rule should do"
            },
            {
              "name": "project_id",
              "required": true,
              "description": "Project ID where the rule will be created"
            }
          ]
        },
        {
          "name": "manage_project_users",
          "description": "Manage users in a project (add, remove, update roles)",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project ID"
            },
            {
              "name": "action",
              "required": true,
              "description": "Action to perform: add, remove, update_role"
            },
            {
              "name": "user_info",
              "required": true,
              "description": "User information (email, user_id, role)"
            }
          ]
        },
        {
          "name": "create_scheduled_task",
          "description": "Create a scheduled task that runs on a schedule",
          "arguments": [
            {
              "name": "name",
              "required": true,
              "description": "Task name"
            },
            {
              "name": "cron",
              "required": true,
              "description": "Cron expression (e.g., '0 2 * * *' for daily at 2 AM)"
            },
            {
              "name": "command",
              "required": true,
              "description": "Command or tool to execute"
            }
          ]
        },
        {
          "name": "handle_validation_error",
          "description": "Guide for handling validation errors",
          "arguments": [
            {
              "name": "tool_name",
              "required": true,
              "description": "Name of the tool that failed"
            },
            {
              "name": "validation_errors",
              "required": true,
              "description": "List of validation errors"
            }
          ]
        },
        {
          "name": "execute_logic_command",
          "description": "Execute a logic rule immediately",
          "arguments": [
            {
              "name": "logic_id",
              "required": true,
              "description": "Logic rule ID (UUID)"
            },
            {
              "name": "event_data",
              "required": false,
              "description": "Event data to pass to the logic rule"
            }
          ]
        },
        {
          "name": "use_processor_in_logic",
          "description": "Use a processor in a logic rule",
          "arguments": [
            {
              "name": "processor_name",
              "required": true,
              "description": "Name of the processor to use"
            },
            {
              "name": "action",
              "required": true,
              "description": "Processor action to execute"
            },
            {
              "name": "parameters",
              "required": true,
              "description": "Processor-specific parameters"
            }
          ]
        },
        {
          "name": "batch_operations",
          "description": "Execute multiple commands in batch",
          "arguments": [
            {
              "name": "commands",
              "required": true,
              "description": "Array of command objects to execute"
            }
          ]
        },
        {
          "name": "find_entity_by_field",
          "description": "Find any entity by any field using DNA CRUD",
          "arguments": [
            {
              "name": "target_entity",
              "required": true,
              "description": "Entity type (e.g., 'data_users_user', 'data_projects_8dna')"
            },
            {
              "name": "filters",
              "required": true,
              "description": "Filter criteria (any field of the entity)"
            }
          ]
        },
        {
          "name": "agentstack_agent_social_participant",
          "description": "How to participate in AgentSocial chats and graph via MCP social.* (delegated operator token, polling, contracts).",
          "arguments": []
        },
        {
          "name": "agentstack_system_instructions",
          "description": "System instructions for AgentStack: when to use which tools, projects, users, and resources (agentstack://me, agentstack://projects/{id}). Use tools for actions; use resources for context.",
          "arguments": []
        },
        {
          "name": "agentstack_session_setup",
          "description": "Mandatory session ladder: authenticate, bind context.project_id, then agents.work_next (recipe mcp_work_loop_v1). Catalog search is fallback.",
          "arguments": []
        },
        {
          "name": "agentstack_agentcrush_remediation_v1",
          "description": "AgentCrush pid 894280 — generation anchor discipline, StackScript promote, hosted validation.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "AgentCrush tenant project"
            }
          ]
        },
        {
          "name": "agentstack_stackscript",
          "description": "StackScript TS subset → SSBC via MCP script.* (not Logic JSON rules).",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Tenant project id"
            }
          ]
        },
        {
          "name": "agentstack_work_graph",
          "description": "Work Graph skill: agents.work_next, plan_get, claim, when blocked, viewer_urls. Same loop for every MCP protocol version.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Tenant project id (head or organ)"
            }
          ]
        },
        {
          "name": "agentstack_closed_loop_autonomy",
          "description": "Work Graph after session: agents.work_next → follow packet.next_action (often plan_claim → plan_execute when mcp_write). Read keys: work_next without claim. Catalog only if no packet.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Tenant project id (head or organ)"
            }
          ]
        },
        {
          "name": "agentstack_commerce_flows",
          "description": "Commerce: MCP payments/assets/wallets vs REST marketplace and exchange; canonical action names and typical chains.",
          "arguments": [
            {
              "name": "use_case",
              "required": false,
              "description": "Optional hint: game_economy, saas_billing, marketplace, exchange"
            }
          ]
        },
        {
          "name": "agentstack_project_setup",
          "description": "Step-by-step guide for bootstrapping a complete project with economy, RBAC, logic, scheduler, and API keys",
          "arguments": [
            {
              "name": "use_case",
              "required": false,
              "description": "Optional: game, saas, ecommerce, social, backend_api"
            }
          ]
        },
        {
          "name": "agentstack_platform_subscription_grant",
          "description": "Platform owner: grant personal Premium/VIP to a user or Launch/Business/Scale to a project via buffs",
          "arguments": [
            {
              "name": "plane",
              "required": true,
              "description": "personal | project"
            },
            {
              "name": "tier",
              "required": true,
              "description": "premium|vip OR starter|basic|pro|enterprise"
            },
            {
              "name": "entity_id",
              "required": true,
              "description": "user_id (personal) or project_id (project)"
            }
          ]
        },
        {
          "name": "agentstack_tenant_subscription_monetization",
          "description": "Tenant project sells subscription SKUs to end users — buff templates, assets, checkout, grant",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Tenant flagship project id"
            },
            {
              "name": "tenant_plan_slug",
              "required": true,
              "description": "Tenant SKU slug (e.g. pro_monthly)"
            }
          ]
        },
        {
          "name": "agentstack_tenant_buff_grant",
          "description": "Tenant operator grants subscription buff or inventory to an end user in their project",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Tenant project id (>1)"
            },
            {
              "name": "user_id",
              "required": true,
              "description": "Buyer / end-user id"
            },
            {
              "name": "plan_id",
              "required": true,
              "description": "Tenant SKU slug (e.g. pro_monthly)"
            }
          ]
        },
        {
          "name": "agentstack_project_member_ops",
          "description": "Add or promote a project member (admin/member/read) — operator and owner paths",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Target project id"
            },
            {
              "name": "user_query",
              "required": true,
              "description": "Email or @username to resolve"
            },
            {
              "name": "role",
              "required": false,
              "description": "admin | member | read | write"
            }
          ]
        },
        {
          "name": "agentstack_generation_canary",
          "description": "Deprecated alias — use agentstack_tenant_8dna_supply for tenant 8DNA generation supply.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id with sandbox generations"
            }
          ]
        },
        {
          "name": "agentstack_showcase_ops",
          "description": "Ecosystem /showcase gallery catalog on project_id=1 — read, drift, upsert cards, probe health.",
          "arguments": []
        },
        {
          "name": "agentstack_showcase_vps_ops",
          "description": "Platform proof showcase (1438–1443): VPS sources sync, hosting.site.build, republish, verify.",
          "arguments": []
        },
        {
          "name": "agentstack_plan_graph",
          "description": "Project plan graph (8DNA task_list v2): read, merge, focus run, affinities, F1 promote",
          "arguments": []
        },
        {
          "name": "agentstack_plan_backlog_ops",
          "description": "Plan backlog safe cycle: goal-route → plan_process_backlog (preview) → review → plan_apply_proposal (CAS). Telegram/Copilot/MCP parity.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id with orchestrator plan graph"
            }
          ]
        },
        {
          "name": "agentstack_inverse_orchestrator_playbook",
          "description": "Inverse orchestrator for external MCP clients: instruction_packet allowed_actions, advance_run_inverse cursor, wave_xix_atoms on agents.* steps",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Tenant project id for work-graph execution"
            }
          ]
        },
        {
          "name": "agentstack_safe_project_cycle",
          "description": "Master safe cycle: session → preflight → domain mutate in sandbox → verify → diff → gates → promote. All tenant domains via MCP.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Tenant project id"
            }
          ]
        },
        {
          "name": "agentstack_tenant_8dna_supply",
          "description": "Tenant 8DNA supply chain: auto-fork, diff vs prod, gates, promote, realign, deploy boundary.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Tenant project id (e.g. flagship Unity tenant)"
            }
          ]
        },
        {
          "name": "agentstack_tenant_ops_mcp_first",
          "description": "MCP-first tenant heal: mentor bots, sandbox verify, promote — no local code unless MCP blocked.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Tenant project id"
            }
          ]
        },
        {
          "name": "agentstack_grants_os_content",
          "description": "Grant OS content plane: catalog, CRM, earning lanes, anchor/W0 — MCP write paths (ecosystem owner).",
          "arguments": [
            {
              "name": "program_id",
              "required": false,
              "description": "Optional grant program_id to scope earning synergy filter"
            }
          ]
        },
        {
          "name": "agentstack_business_organism",
          "description": "Business organism MCP: head project, organ children, tariff, command snapshot.",
          "arguments": [
            {
              "name": "head_project_id",
              "required": false,
              "description": "Business head project id (optional for bootstrap)"
            }
          ]
        },
        {
          "name": "agentstack_tenant_business_assistant",
          "description": "End-to-end tenant business assistant via MCP recipe (head, CRM organ, operator, Telegram).",
          "arguments": []
        },
        {
          "name": "agentstack_business_flows",
          "description": "Quick reference for 12 real business scenarios with tool synergies and cross-flow patterns",
          "arguments": [
            {
              "name": "scenario",
              "required": false,
              "description": "Optional: bootstrap, saas_trial, game_economy, loyalty, ecommerce, automation, content, social, b2b, campaign, usage_billing, matchmaking"
            }
          ]
        },
        {
          "name": "agentstack_api_key_safety",
          "description": "Guide for creating and using API keys safely with service_caps restrictions",
          "arguments": []
        },
        {
          "name": "agentstack_paradigm_shift",
          "description": "Paradigm shift: buffs as timers, users as containers, projects as shared state",
          "arguments": []
        },
        {
          "name": "agentstack_execute_budget",
          "description": "Sync 60s mcp_batch vs heavy LLM steps; async jobs and discovery.job_status",
          "arguments": []
        },
        {
          "name": "agentstack_write_modes",
          "description": "How to edit text and collections: prefer search_replace / unified_diff; merge lists by key; never paste a truncated window as the full body",
          "arguments": []
        },
        {
          "name": "agentstack_text_editor",
          "description": "Cross-surface text edit ladder: search_replace and fuzzy unified_diff (same engine as App Studio). Prefer over full-body replace.",
          "arguments": []
        },
        {
          "name": "agentstack_read_bootstrap",
          "description": "Read-only MCP bootstrap with continueOnError; omit apikeys.list without api_keys cap",
          "arguments": []
        },
        {
          "name": "agentstack_social_messenger",
          "description": "Complete AI guide for using the built-in messenger and social network via MCP (social.chat.*, social.channels.*, social.friends.*, social.public.*)",
          "arguments": []
        },
        {
          "name": "agentstack_channel_setup",
          "description": "Unified Channel Plane: enroll delivery sources, category prefs, notifications.deliver, and channels.* MCP tools",
          "arguments": []
        },
        {
          "name": "agentstack_agents_fleet",
          "description": "Agents Fleet: configure, enqueue, orchestrate.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_integrations_hub",
          "description": "Integration Hub: recipes, connections, webhooks, diagnostics.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_crm_workspace",
          "description": "CRM workspace: contacts, deals, pipeline, import.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_hosted_vertical",
          "description": "Hosted vertical SaaS: EDITFLOW wire, bootstrap, tenant UI facades.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Flagship tenant project id"
            }
          ]
        },
        {
          "name": "agentstack_key2unity_site",
          "description": "Key2Unity auth portal /s/1444/key2unity/: persona, bucket, dual bot identity, publish.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Unity mentor flagship (1444)"
            }
          ]
        },
        {
          "name": "agentstack_hosting_storefront",
          "description": "Hosted shop: create products, list them for sale, publish /s/, take checkout.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_hosting_edit_site",
          "description": "Change an already published /s/ site with snapshot and release promote (not quickstart).",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_hosting_static_landing",
          "description": "Publish a single HTML landing page to hosted /s/ (agent recipe).",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_hosting_workspace_build",
          "description": "Build static or node_vite site from bucket workspace sources.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_showcase_arcanestack_ops",
          "description": "ArcaneStack pid 1438: git journal push ladder + optional showcase.arcanestack.ensure_rules.",
          "arguments": []
        },
        {
          "name": "agentstack_hosting_git_journal",
          "description": "Per-bucket git journal: init, push dev/main, poll builds, preview and prod URLs.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_deploy_surface",
          "description": "Resolve deploy surface (site vs app vs shop vs service) before mutating.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            },
            {
              "name": "intent",
              "required": false,
              "description": "Operator goal text"
            }
          ]
        },
        {
          "name": "agentstack_hosting_react_dist",
          "description": "Upload React/Vite dist ZIP or let import_archive build sources on the worker.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_hosting_file_edit",
          "description": "Edit one UTF-8 file in hosted bucket working tree via patch.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_bots_studio",
          "description": "Bots Fleet studio: templates, brain, handoff, broadcast.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_bot_message_bus",
          "description": "Agent-to-agent messaging on bot message bus (@handle, webhook push, inbox poll).",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_support_staff",
          "description": "Project support staff inbox and AI binding.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_knowledge_mentor",
          "description": "Knowledge platform: config leaf, KB ingest, playground (heavy), heal index.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_knowledge_answer_tune",
          "description": "Tune mentor prompt → playground → promote (UF_KNOWLEDGE_PROMPT_TUNE).",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_knowledge_safety_tune",
          "description": "Safety playbook overlay → safety.evaluate → promote.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_context_lanes",
          "description": "Pick a context lane, ingest task docs, and tune caps in 8DNA.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_guidance_compass",
          "description": "Platform Compass playbooks: guidance.list, match_playbook, start_path, complete_step.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_app_studio",
          "description": "Headless React app studio. Same verbs for an external agent and the project orchestrator.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_project_orchestrator",
          "description": "Project AI orchestrator — workspace vs messenger vs bots, generation F1, RAG memory.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_rag_memory_orchestrator",
          "description": "KB vs episodic memory disambiguation for orchestrator agents.",
          "arguments": []
        },
        {
          "name": "agentstack_project_treasury",
          "description": "Project wallet treasury vs personal wallets vs AgentNet.",
          "arguments": [
            {
              "name": "project_id",
              "required": true,
              "description": "Project id"
            }
          ]
        },
        {
          "name": "agentstack_use_case_game",
          "description": "Build games with player management, game logic, and monetization",
          "arguments": []
        },
        {
          "name": "agentstack_use_case_saas",
          "description": "Build SaaS with trials, subscriptions, and usage tracking",
          "arguments": []
        },
        {
          "name": "agentstack_use_case_ecommerce",
          "description": "Build online stores with products, cart, and payments",
          "arguments": []
        },
        {
          "name": "agentstack_use_case_social",
          "description": "AgentSocial: messenger, friends graph, PAS, public index via social.* MCP actions",
          "arguments": []
        },
        {
          "name": "agentstack_use_case_backend_api",
          "description": "Build REST APIs with CRUD, webhooks, and automation",
          "arguments": []
        },
        {
          "name": "agentstack_use_case_project_setup",
          "description": "Bootstrap complete projects: economy, RBAC, logic rules battery, scheduler, FAP, API keys, RAG",
          "arguments": []
        }
      ]
    },
    "instructions": "AgentStack MCP — one tool: agentstack.execute (POST /mcp). After VPS backend restart, first agents.work_next may fail while MCP tools import — wait ~15s and retry once (not a plan graph bug). Bound project: agents.work_next (recipe mcp_work_loop_v1) before catalog search. discovery.search is fallback only. Authenticate first: GET /mcp/connect → /mcp/.well-known/oauth-authorize (PKCE), IDE Device Code POST /api/oauth2/device/authorize, or MCP auth.login. If this client cannot complete OAuth, use the user's API key: header X-API-Key or Authorization: Bearer <user API key> from the profile. Session probe: auth.get_profile (alias auth.me). Bind context.project_id, then agents.work_next. Packs session.v1/batch.v1: discovery.list exposes execute_budget.packs. Work Graph skill: /mcp/prompts/get?name=agentstack_work_graph (agentstack://instructions/work-graph). If session_ready or mutation_allowed, do not log in again and do not switch_project. discovery.search only when packet.next_action is absent. discovery.describe for one action. preflight.check before writes. Empty lists are valid. Diagnose before repair. A timeout retries the same idempotency key. Do not call a heavy_llm action only to read state. A page at /s/{id}/ uses the hosted cookie, not operator MCP auth.login. Playbook: /mcp/prompts/get?name=agentstack_session_setup. When discovery.search returns response_mode=workflow, run that step. Do not treat catalog_page as the command. OAuth often binds ecosystem project_id=1 — override with tenant id."
  },
  "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."
}