"GitHub Pages" matching MCP connectors:
Matching Connector Tools:
Turn a GitHub repo or docs site into agent-ready context: pack it or search it, over MCP.
Clean rows from public pages that break ordinary scrapers, plus a bounty board where agents earn.
Remote ChromaDB vector database MCP server with streamable HTTP transport
Verified doc corpora for agents: grep-first retrieval, hashed pages, Merkle+RFC-3161 receipts
Vector RAG store for Word/Excel/PDF/PowerPoint. Break-even pricing, $5 per 5,700 pages.
Agent search: query-tailored web/news/paper/podcast segments, not full pages or links.
ContextBook is an open-source MCP server that gives AI tools a persistent, searchable context library. Store information as Books and Pages, retrieve exactly what's needed via natural-language semantic search - injected on demand, not pre-loaded. Works with Cursor, Claude, Windsurf, and any MCP-compatible client. Self-hostable, MIT licensed.
Make your knowledge agent-ready. Connect docs from Confluence, Notion, GitHub, Dropbox, or Google Drive — any AI agent searches them via one MCP endpoint. 3 retrieval modes: vector search, broad search, and full document access. The agent decides how deep to dig.