CrawlCheck MCP

CrawlCheck provides a verification layer for agentic web interactions by offering signed answers about domains before an agent acts. The MCP server allows agents to check what a site permits, what it serves, and whether to read, cite, connect, or transact. It includes tools to scan remote MCP servers for poisoning, compare tools against a lockfile, and verify visitor authenticity, ensuring safe and compliant agent behavior.

Endpoint and access

No sign-in: your client connects and lists tools immediately, with no account or key.

No sign-inEndpoint checked 2026-10-18Operated by CrawlCheck

MCP endpoint (Streamable HTTP)

https://crawlcheck.io/mcp

Vendor documentation

What you can do with it

Verify domain permissions and decisions before agent actions
Scan remote MCP servers for tool poisoning
Compare server tools against a local lockfile
Verify visitor authenticity for specific sites

Tools advertised by the last live check:

preflight
best_source
resolve_domain
field_check
scan_domain
list_verified_capabilities
mcp_servers
verify_crawler_log
corpus_state
resolve_robots
draft_llms
fix_robots
fix_entitymap
video_check
video_channel
video_site
registry_lookup
crawler_path
public_counts
telemetry
fix_mostly_code
fix_stale_cache
fix_machine_chain
explain_finding
machine_record

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http crawlcheck-mcp https://crawlcheck.io/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add crawlcheck-mcp --url https://crawlcheck.io/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable crawlcheck-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "crawlcheck-mcp": {
      "url": "https://crawlcheck.io/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

{
  "mcpServers": {
    "crawlcheck-mcp": {
      "type": "streamableHttp",
      "url": "https://crawlcheck.io/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start crawlcheck-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "crawlcheck-mcp": {
      "type": "http",
      "url": "https://crawlcheck.io/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http crawlcheck-mcp https://crawlcheck.io/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "crawlcheck-mcp": {
      "url": "https://crawlcheck.io/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "crawlcheck-mcp": {
      "serverUrl": "https://crawlcheck.io/mcp"
    }
  }
}

See all 1,227

Do you run CrawlCheck MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing