AI & Machine Learning
crawlcensus.com
Analyzes and audits websites' robots.txt and accessibility for AI crawlers, providing reports and statistics on AI agent access.
ENDPOINT 1
https://crawlcensus.com/mcp
MCP server metadata
- Name
- crawl-census
- Version
- 1.0.0
Audit how AI crawlers and answer engines can read a website, and query the public census of who blocks whom.
Known tools 6
site_reportReturn the most recent stored audit for a domain without triggering a new scan.
Inferred read-onlycensus_statsCorpus-level statistics: how many measured domains block each AI crawler, mean access score, llms.
Inferred read-onlycrawl_preflightDecide whether a crawler may fetch a list of domains before spending requests on them.
Inferred read-onlyagent_profileWhat this census measures and publishes about one AI crawler: how often it is disallowed in robots.
Inferred read-onlycensus_factsEvery headline finding from the census as discrete, dated records rather than prose.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.crawl-census]
url = "https://crawlcensus.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"crawl-census": {
"type": "http",
"url": "https://crawlcensus.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: crawl-census
Remote MCP URL: https://crawlcensus.com/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"crawl-census": {
"url": "https://crawlcensus.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"crawl-census": {
"type": "http",
"url": "https://crawlcensus.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "crawl-census",
"transport": "streamable-http",
"url": "https://crawlcensus.com/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.