doc-scraper MCP
A Go-based web crawler that scrapes documentation sites, converts content to clean Markdown, and serves the local corpus to AI agents via MCP. It supports offline search and reading of documentation without network access, detecting various frameworks like Docusaurus, Sphinx, and VitePress.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Offline full-text search of documentation via BM25
- Read specific documentation pages locally
- Crawl and convert docs sites to Markdown for RAG
- Incremental re-crawls to keep documentation fresh
Source and maintenance
Community listingRegistry 2.24.1
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
https://github.com/Sriram-PR/doc-scraper/releases/download/v2.24.1/doc-scraper.mcpb
mcpbSHA-256 supplied
https://github.com/Sriram-PR/doc-scraper/releases/download/v2.24.1/doc-scraper.mcpb package definition
{
"transport": "stdio",
"fileSha256": "64e007f62c767c54d4c20e95ed3ae0b4a02cc2a95e77a8bedb02a9497c3a29ad",
"identifier": "https://github.com/Sriram-PR/doc-scraper/releases/download/v2.24.1/doc-scraper.mcpb",
"registryType": "mcpb"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Let your agent find its tools
Find servers like doc-scraper MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.