Pages, crawls and URL batches as clean Markdown and JSON for AI agents, with an Evidence Record.
Connect Remote server
claude mcp add --transport http octocrawl https://mcp.octocrawl.dev/mcp{
"mcpServers": {
"octocrawl": {
"url": "https://mcp.octocrawl.dev/mcp"
}
}
}{
"servers": {
"octocrawl": {
"type": "http",
"url": "https://mcp.octocrawl.dev/mcp"
}
}
}Settings > Connectors > Add custom connector
URL: https://mcp.octocrawl.dev/mcpTools 2 found in our last check
scrapeRead one URL as Markdown with its Evidence Record (final URL, fetch time, HTTP status, robots.txt decision, hashes), over HTTP first and in the browser when the page needs it. Not for: many URLs or a whole site section. Compact by default; debug adds the full audit. warnings nam…
mapList a site's URLs without reading each page: the start page's links (read over HTTP alone) and the entries of the sitemaps the site declares, within one deadline. URLs stay in scope (the start host and its www twin, the start path's subtree, assets left out, similar URLs folded…
Details
| Endpoint | https://mcp.octocrawl.dev/mcp (Streamable HTTP) |
| Endpoint | https://mcp.octocrawl.dev/mcp-oauth (Streamable HTTP) |
| Package | @octocrawl/[email protected] (NPM, stdio) |
| First published | 11 Nov 2026 |
| Last updated | 11 Nov 2026 |
| Registry name | io.github.77777R7/octocrawl |
More search and web servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.