{
  "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": "www.benchleader.com",
    "site": "benchleader.com",
    "addresses": [
      {
        "address": "104.21.66.217",
        "endpoints": 2,
        "shared_infrastructure": false,
        "network": {
          "asn": 13335,
          "name": "CLOUDFLARENET - Cloudflare, Inc.",
          "prefix": "104.21.64.0/19",
          "country": "US"
        }
      },
      {
        "address": "172.67.164.175",
        "endpoints": 2,
        "shared_infrastructure": false,
        "network": {
          "asn": 13335,
          "name": "CLOUDFLARENET - Cloudflare, Inc.",
          "prefix": "172.67.160.0/20",
          "country": "US"
        }
      },
      {
        "address": "2606:4700:3032::ac43:a4af",
        "endpoints": 2,
        "shared_infrastructure": false,
        "network": {
          "asn": 13335,
          "name": "CLOUDFLARENET - Cloudflare, Inc.",
          "prefix": "2606:4700:3032::/48",
          "country": "US"
        }
      },
      {
        "address": "2606:4700:3037::6815:42d9",
        "endpoints": 2,
        "shared_infrastructure": false,
        "network": {
          "asn": 13335,
          "name": "CLOUDFLARENET - Cloudflare, Inc.",
          "prefix": "2606:4700:3037::/48",
          "country": "US"
        }
      }
    ],
    "addresses_recorded": true,
    "address_history": [
      {
        "addresses": [
          "104.21.66.217",
          "172.67.164.175",
          "2606:4700:3032::ac43:a4af",
          "2606:4700:3037::6815:42d9"
        ],
        "first_seen": "2026-11-22T07:59:02.351Z",
        "last_seen": "2026-11-22T07:59:02.351Z",
        "checks": 1
      }
    ],
    "hosting": [
      {
        "value": "Cloudflare",
        "evidence": "Server header \"cloudflare\""
      }
    ],
    "software": [],
    "server_info": {
      "name": "benchleader",
      "version": "1.0.0",
      "protocol_version": "2025-06-18"
    },
    "headers": {
      "server": "cloudflare",
      "access-control-allow-origin": "*"
    },
    "auth": null
  },
  "related": {
    "same_address": {
      "total": 1,
      "sample": [
        {
          "id": "28311",
          "url": "https://mp4.now/mcp",
          "server_name": "io.github.chrisyau83/mp4-now",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T19:32:02.361Z"
        }
      ]
    },
    "same_site": {
      "total": 0,
      "sample": []
    },
    "same_tool_list": {
      "total": 0,
      "sample": []
    },
    "same_publisher": {
      "publisher": "com.benchleader",
      "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": "7256",
    "server_name": "com.benchleader/benchleader",
    "url": "https://www.benchleader.com/mcp",
    "host": "www.benchleader.com",
    "transport": "streamable-http",
    "last_checked_at": "2026-11-22T07:59:02.351Z",
    "last_state": "listed",
    "last_detail": null,
    "consecutive_failures": 0,
    "current_sha": "63b37a1fa0fdb125c0f263b15aa08d8463fe9b91d61c5c442e945cb77fdc00e7",
    "first_listed_at": "2026-11-21T07:22:01.368Z",
    "created_at": "2026-11-21T05:20:09.393Z",
    "resolved_addresses": [
      "104.21.66.217",
      "172.67.164.175",
      "2606:4700:3032::ac43:a4af",
      "2606:4700:3037::6815:42d9"
    ]
  },
  "server": {
    "name": "com.benchleader/benchleader",
    "title": "BenchLeader",
    "description": "Daily LLM leaderboard from independent benchmarks: ranks, scores, prices, speed and comparisons.",
    "version": "1.0.0",
    "registry_status": "active",
    "repository_url": null,
    "website_url": "https://www.benchleader.com/mcp",
    "published_at": "2026-10-31T17:58:47.880Z",
    "updated_at": "2026-10-31T17:58:47.880Z",
    "first_seen": "2026-11-21T05:20:08.805Z"
  },
  "other_endpoints": [],
  "intel": {
    "capabilities": [],
    "evm_addresses": [],
    "chains": [],
    "tokens": [],
    "computed_at": "2026-11-22T15:02:06.710Z"
  },
  "operator": {
    "key": "benchleader.com",
    "name": "benchleader.com",
    "platform": false
  },
  "needs_sign_in": false,
  "reachability": {
    "window_days": 30,
    "checks": 2,
    "answered": 2,
    "answered_percent": 100,
    "avg_listing_latency_ms": 159,
    "first_check_in_window": "2026-11-21T07:22:01.368Z",
    "consecutive_failures_now": 0,
    "days": [
      {
        "day": "2026-11-21",
        "checks": 1,
        "answered": 1,
        "last_state": "listed"
      },
      {
        "day": "2026-11-22",
        "checks": 1,
        "answered": 1,
        "last_state": "listed"
      }
    ]
  },
  "tool_list": {
    "sha256": "63b37a1fa0fdb125c0f263b15aa08d8463fe9b91d61c5c442e945cb77fdc00e7",
    "tools": 7,
    "resources": 0,
    "prompts": 0,
    "first_seen": "2026-11-21T07:22:01.561Z",
    "tool_names": [
      "get_leaderboard",
      "search_models",
      "get_model",
      "compare_models",
      "list_benchmarks",
      "get_benchmark",
      "about_benchleader"
    ],
    "declared": {
      "tools": [
        {
          "name": "get_leaderboard",
          "title": "BenchLeader leaderboard",
          "description": "The BenchLeader Index leaderboard of large language models: a daily composite of independent public benchmarks, one row per model (its best reasoning-effort configuration) as on the homepage. Optionally rank by one category score (coding, agentic, reasoning, math, knowledge…), list every model × effort configuration, or filter to open-weights models or one developer. Paged.",
          "inputSchema": {
            "type": "object",
            "properties": {
              "limit": {
                "type": "integer",
                "default": 20,
                "maximum": 100,
                "minimum": 1,
                "description": "How many rows to return (at most 100)."
              },
              "offset": {
                "type": "integer",
                "default": 0,
                "minimum": 0,
                "description": "Rows to skip, for paging (use next_offset from the previous page)."
              },
              "category": {
                "type": "string",
                "description": "Rank by this category score instead of the overall Index, e.g. coding, agentic, reasoning, math, knowledge, instruction, multimodal, long_context."
              },
              "developer": {
                "type": "string",
                "description": "Only models from this developer, e.g. OpenAI, Anthropic, Google, DeepSeek."
              },
              "configurations": {
                "type": "boolean",
                "default": false,
                "description": "List every ranked model × reasoning-effort configuration rather than one row per model."
              },
              "open_weights_only": {
                "type": "boolean",
                "default": false,
                "description": "Only models with downloadable weights."
              }
            },
            "additionalProperties": false
          },
          "annotations": {
            "title": "BenchLeader leaderboard",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "search_models",
          "title": "Search models",
          "description": "Find models by name, alias, id or developer (\"opus\", \"gemini 4\", \"deepseek\"). Returns each match's id, rank, Index and reasoning-effort configurations, for use with get_model and compare_models.",
          "inputSchema": {
            "type": "object",
            "required": [
              "query"
            ],
            "properties": {
              "limit": {
                "type": "integer",
                "default": 10,
                "maximum": 25,
                "minimum": 1,
                "description": "How many matches to return (at most 25)."
              },
              "query": {
                "type": "string",
                "description": "Model name, alias, id or developer."
              }
            },
            "additionalProperties": false
          },
          "annotations": {
            "title": "Search models",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "get_model",
          "title": "Model details",
          "description": "One model's BenchLeader profile: Index and rank, category scores, list price, speed, latency, context window, its other reasoning-effort configurations, and its strongest independent benchmark results (each with its board rank, publisher and source link).",
          "inputSchema": {
            "type": "object",
            "required": [
              "model"
            ],
            "properties": {
              "model": {
                "type": "string",
                "description": "Model id (\"claude-opus-5-5\"), configuration id (\"gpt-6-astra@max\"), page URL or name."
              },
              "effort": {
                "type": "string",
                "description": "Reasoning-effort configuration to show (none, low, medium, high, xhigh, max…). Defaults to the best-ranked one."
              },
              "results_limit": {
                "type": "integer",
                "default": 10,
                "maximum": 50,
                "minimum": 1,
                "description": "How many benchmark results to return (at most 50)."
              }
            },
            "additionalProperties": false
          },
          "annotations": {
            "title": "Model details",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "compare_models",
          "title": "Compare two models",
          "description": "Head-to-head comparison of two models with BenchLeader's verdict: who leads on quality (a lead is claimed only outside the combined margin of error), price and speed ratios, category-by-category wins, when to choose each, and shared benchmark results. Links the comparison page.",
          "inputSchema": {
            "type": "object",
            "required": [
              "model_a",
              "model_b"
            ],
            "properties": {
              "model_a": {
                "type": "string",
                "description": "First model: id, configuration id, page URL or name."
              },
              "model_b": {
                "type": "string",
                "description": "Second model: id, configuration id, page URL or name."
              },
              "effort_a": {
                "type": "string",
                "description": "Reasoning effort for model_a (defaults to its best-ranked configuration)."
              },
              "effort_b": {
                "type": "string",
                "description": "Reasoning effort for model_b (defaults to its best-ranked configuration)."
              }
            },
            "additionalProperties": false
          },
          "annotations": {
            "title": "Compare two models",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "list_benchmarks",
          "title": "List benchmarks",
          "description": "The benchmarks BenchLeader reads: what each measures, publisher, category, whether it feeds the Index (and its weight), how many models it covers, status and caveats. Filter by category or a search query. Paged.",
          "inputSchema": {
            "type": "object",
            "properties": {
              "limit": {
                "type": "integer",
                "default": 50,
                "maximum": 100,
                "minimum": 1,
                "description": "How many benchmarks to return (at most 100)."
              },
              "query": {
                "type": "string",
                "description": "Search benchmark names, ids, aliases and publishers (\"swe-bench\", \"arc\", \"epoch\")."
              },
              "offset": {
                "type": "integer",
                "default": 0,
                "minimum": 0,
                "description": "Rows to skip, for paging (use next_offset from the previous page)."
              },
              "category": {
                "type": "string",
                "description": "Only this category, e.g. coding, agentic, reasoning, math, knowledge."
              },
              "in_index_only": {
                "type": "boolean",
                "default": false,
                "description": "Only benchmarks that feed the BenchLeader Index."
              }
            },
            "additionalProperties": false
          },
          "annotations": {
            "title": "List benchmarks",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "get_benchmark",
          "title": "Benchmark details",
          "description": "One benchmark: what it measures, unit, publisher and source, whether and how much it counts in the BenchLeader Index, status and caveats, and its top models (one row per model, best result first).",
          "inputSchema": {
            "type": "object",
            "required": [
              "benchmark"
            ],
            "properties": {
              "limit": {
                "type": "integer",
                "default": 10,
                "maximum": 25,
                "minimum": 1,
                "description": "How many top models to return (at most 25)."
              },
              "benchmark": {
                "type": "string",
                "description": "Benchmark id (\"gpqa_diamond\"), name (\"SWE-bench Verified\"), alias or page URL."
              }
            },
            "additionalProperties": false
          },
          "annotations": {
            "title": "Benchmark details",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "about_benchleader",
          "title": "About BenchLeader",
          "description": "What BenchLeader is, how the BenchLeader Index is computed, the current method version, data date and update cadence, coverage counts, licence and how to cite it.",
          "inputSchema": {
            "type": "object",
            "properties": {},
            "additionalProperties": false
          },
          "annotations": {
            "title": "About BenchLeader",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        }
      ],
      "tools_omitted": 0,
      "resources": [],
      "prompts": []
    },
    "instructions": "BenchLeader ranks large language models daily on the BenchLeader Index, a composite of independent public benchmarks (50 = average model, 15 = one standard deviation). Start with get_leaderboard or search_models; use get_model and compare_models for details, list_benchmarks and get_benchmark for the boards, about_benchleader for method and licence. Rows are model × reasoning-effort configurations; ids look like \"model-id@effort\". Cite the url fields when you quote figures."
  },
  "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."
}