{
  "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": "datacensus.org",
    "site": "datacensus.org",
    "addresses": [
      {
        "address": "172.67.128.96",
        "endpoints": 1,
        "shared_infrastructure": false,
        "network": {
          "asn": 13335,
          "name": "CLOUDFLARENET - Cloudflare, Inc.",
          "prefix": "172.67.128.0/20",
          "country": "US"
        }
      },
      {
        "address": "104.21.0.232",
        "endpoints": 1,
        "shared_infrastructure": false,
        "network": {
          "asn": 13335,
          "name": "CLOUDFLARENET - Cloudflare, Inc.",
          "prefix": "104.21.0.0/20",
          "country": "US"
        }
      },
      {
        "address": "2606:4700:3037::ac43:8060",
        "endpoints": 1,
        "shared_infrastructure": false,
        "network": {
          "asn": 13335,
          "name": "CLOUDFLARENET - Cloudflare, Inc.",
          "prefix": "2606:4700:3037::/48",
          "country": "US"
        }
      },
      {
        "address": "2606:4700:3031::6815:e8",
        "endpoints": 1,
        "shared_infrastructure": false,
        "network": {
          "asn": 13335,
          "name": "CLOUDFLARENET - Cloudflare, Inc.",
          "prefix": "2606:4700:3031::/48",
          "country": "US"
        }
      }
    ],
    "addresses_recorded": true,
    "address_history": [
      {
        "addresses": [
          "172.67.128.96",
          "104.21.0.232",
          "2606:4700:3037::ac43:8060",
          "2606:4700:3031::6815:e8"
        ],
        "first_seen": "2026-11-21T19:06:01.594Z",
        "last_seen": "2026-11-21T19:06:01.594Z",
        "checks": 1
      }
    ],
    "hosting": [
      {
        "value": "Cloudflare",
        "evidence": "Server header \"cloudflare\""
      }
    ],
    "software": [],
    "server_info": {
      "name": "datacensus",
      "version": "0.1.0",
      "protocol_version": "2025-06-18"
    },
    "headers": {
      "server": "cloudflare",
      "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": "org.datacensus",
      "total": 0,
      "sample": []
    },
    "same_repository": {
      "repository_url": "https://github.com/jirizaloudek/agentwebcensus",
      "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": "45172",
    "server_name": "org.datacensus/agents",
    "url": "https://datacensus.org/mcp",
    "host": "datacensus.org",
    "transport": "streamable-http",
    "last_checked_at": "2026-11-21T19:06:01.594Z",
    "last_state": "listed",
    "last_detail": null,
    "consecutive_failures": 0,
    "current_sha": "862d0e28beee083ca9476a5517534c579cc9fbf504b7d33607c88ce6a99db693",
    "first_listed_at": "2026-11-21T19:06:01.594Z",
    "created_at": "2026-11-21T13:10:02.655Z",
    "resolved_addresses": [
      "172.67.128.96",
      "104.21.0.232",
      "2606:4700:3037::ac43:8060",
      "2606:4700:3031::6815:e8"
    ]
  },
  "server": {
    "name": "org.datacensus/agents",
    "title": "Agent Web Census",
    "description": "Open data on MCP servers (with live health) and which AI crawlers top websites block.",
    "version": "0.1.0",
    "registry_status": "active",
    "repository_url": "https://github.com/jirizaloudek/agentwebcensus",
    "website_url": "https://agents.datacensus.org",
    "published_at": "2026-11-19T09:01:55.838Z",
    "updated_at": "2026-11-19T09:01:55.838Z",
    "first_seen": "2026-11-21T13:10:01.884Z"
  },
  "other_endpoints": [],
  "intel": {
    "capabilities": [],
    "evm_addresses": [],
    "chains": [],
    "tokens": [],
    "computed_at": "2026-11-22T15:49:08.267Z"
  },
  "operator": {
    "key": "datacensus.org",
    "name": "datacensus.org",
    "platform": false
  },
  "needs_sign_in": false,
  "reachability": {
    "window_days": 30,
    "checks": 1,
    "answered": 1,
    "answered_percent": 100,
    "avg_listing_latency_ms": 139,
    "first_check_in_window": "2026-11-21T19:06:01.594Z",
    "consecutive_failures_now": 0,
    "days": [
      {
        "day": "2026-11-21",
        "checks": 1,
        "answered": 1,
        "last_state": "listed"
      }
    ]
  },
  "tool_list": {
    "sha256": "862d0e28beee083ca9476a5517534c579cc9fbf504b7d33607c88ce6a99db693",
    "tools": 4,
    "resources": 0,
    "prompts": 0,
    "first_seen": "2026-11-21T19:06:01.735Z",
    "tool_names": [
      "find_mcp_servers",
      "mcp_ecosystem_stats",
      "site_ai_crawler_policy",
      "ai_crawler_stats"
    ],
    "declared": {
      "tools": [
        {
          "name": "find_mcp_servers",
          "description": "Search the official MCP Registry (~65,000 servers) by keyword. Matches name, title and description; ranks servers whose remote endpoint passed a live initialize check first, then by number of tools. Returns name, title, description, remote/package types, health (ok = works without auth, auth = alive but needs auth, fail = unreachable), tool count and a registry link.",
          "inputSchema": {
            "type": "object",
            "required": [
              "query"
            ],
            "properties": {
              "limit": {
                "type": "integer",
                "default": 10,
                "maximum": 25,
                "minimum": 1,
                "description": "Max results (1-25)."
              },
              "query": {
                "type": "string",
                "description": "Keywords, e.g. 'postgres database' or 'github issues'."
              },
              "category": {
                "type": "string",
                "description": "Optional category filter, e.g. 'finance & crypto', 'databases' (substring match)."
              },
              "transport": {
                "enum": [
                  "remote",
                  "package",
                  "any"
                ],
                "type": "string",
                "description": "remote = hosted endpoint, package = installable (npm/pypi/...), any (default)."
              },
              "working_only": {
                "type": "boolean",
                "default": true,
                "description": "Only servers whose remote endpoint responded OK or requires auth (default true). Package-only servers are kept unless transport is 'remote'."
              }
            }
          },
          "annotations": {
            "readOnlyHint": true,
            "openWorldHint": false
          }
        },
        {
          "name": "mcp_ecosystem_stats",
          "description": "Headline numbers of the MCP ecosystem: servers in the official registry, new servers in the last 7/30 days, remote vs package share, top package registries and categories, plus the weekly health check of remote servers (share working, requiring auth, failing, median tools and latency).",
          "inputSchema": {
            "type": "object",
            "properties": {}
          },
          "annotations": {
            "readOnlyHint": true,
            "openWorldHint": false
          }
        },
        {
          "name": "site_ai_crawler_policy",
          "description": "Which AI crawlers does a website block in robots.txt? Looks up a domain in our scan of the top 10,000 websites (Tranco list) and returns, per AI bot (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, ...), whether it is blocked, partly restricted or explicitly allowed, plus llms.txt presence.",
          "inputSchema": {
            "type": "object",
            "required": [
              "domain"
            ],
            "properties": {
              "domain": {
                "type": "string",
                "description": "Domain or URL, e.g. 'nytimes.com' or 'https://www.nytimes.com/section'."
              }
            }
          },
          "annotations": {
            "readOnlyHint": true,
            "openWorldHint": false
          }
        },
        {
          "name": "ai_crawler_stats",
          "description": "Aggregate AI-crawler blocking statistics across the top 10,000 websites: percentage of sites with a reachable robots.txt that fully block, partly restrict or explicitly allow each AI bot. Give a bot name for one bot, or omit for the overall table.",
          "inputSchema": {
            "type": "object",
            "properties": {
              "bot": {
                "type": "string",
                "description": "Optional bot name, e.g. 'GPTBot', 'ClaudeBot', 'Google-Extended' (case-insensitive)."
              }
            }
          },
          "annotations": {
            "readOnlyHint": true,
            "openWorldHint": false
          }
        }
      ],
      "tools_omitted": 0,
      "resources": [],
      "prompts": []
    },
    "instructions": "Open data about the AI agent ecosystem from Agent Web Census (agents.datacensus.org): use find_mcp_servers to search ~65k servers of the official MCP Registry (with a weekly live-check of remote endpoints), mcp_ecosystem_stats for headline MCP numbers, site_ai_crawler_policy to see which AI bots a top-10k website blocks in robots.txt, and ai_crawler_stats for aggregate AI-crawler blocking rates. Data is CC BY 4.0; cite Agent Web Census. This service is operated by an AI agent (Claude)."
  },
  "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."
}