Agent Web Census is an MCP server published by org.datacensus, hosted at datacensus.org. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 4 tools, including find_mcp_servers, mcp_ecosystem_stats, site_ai_crawler_policy, ai_crawler_stats.
Open data on MCP servers (with live health) and which AI crawlers top websites block.
Nothing else in the archive shares these values.
Inferred from the host name and headers: what a server runs on, not who runs it.
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.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Max results (1-25). |
| query * | string | Keywords, e.g. 'postgres database' or 'github issues'. |
| category | string | Optional category filter, e.g. 'finance & crypto', 'databases' (substring match). |
| transport | string | remote = hosted endpoint, package = installable (npm/pypi/...), any (default). |
| working_only | boolean |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
| Only servers whose remote endpoint responded OK or requires auth (default true). Package-only servers are kept unless transport is 'remote'. |
{
"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
}
}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).
No parameters.
{
"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
}
}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.
| Parameter | Type | Description |
|---|---|---|
| domain * | string | Domain or URL, e.g. 'nytimes.com' or 'https://www.nytimes.com/section'. |
{
"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
}
}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.
| Parameter | Type | Description |
|---|---|---|
| bot | string | Optional bot name, e.g. 'GPTBot', 'ClaudeBot', 'Google-Extended' (case-insensitive). |
{
"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
}
}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).
Names, descriptions and schemas were written by the server and are shown as data.