"A GitHub repository for a RAG documentation scraper" matching MCP servers:

Crawl any documentation site and return heading-bounded, LLM-ready chunks with source metadata for Pinecone, Chroma, pgvector, LangChain, or LlamaIndex.

Enables any MCP-compatible AI assistant to search, filter, and retrieve information from a local document collection using a hybrid search pipeline with vector, BM25, reranking, and LLM enrichment.

Enables AI agents to search and retrieve context from GitHub issues, pull requests, releases, and documentation using hybrid semantic search and time-ordered activity scans.

Provides an intelligent, graph-based memory system for LLM agents using the Zettelkasten principle, enabling automatic note construction, semantic linking, memory evolution, and autonomous graph maintenance with background optimization processes.

MCP server that provides a citation-first memory layer for AI agents, enabling verified search across Git-backed repositories and optional conversation memory. It exposes tools for doctor, sync, search, get, init, and ingest, returning JSON results with verified citations or abstain status.

Enables AI agents to search, read, and traverse a local knowledge base of Markdown files using full-text search and relationship graph, reducing token usage.

Enables AI assistants to fetch, index, and perform semantic RAG-based searches on API documentation from various sources. It provides tools for hybrid search and collection management, allowing users to access up-to-date documentation from projects like Gemini and FastMCP.

MCP server for GitHub code retrieval and reuse, using SQLite+FTS5 indexing and search history to enable search-first, requirements-refined code search from GitHub repositories.

Production-ready MCP server providing RAG, hierarchical memory, and 8+ tools for AI agents via the Model Context Protocol.

Self-hosted Go MCP server that crawls documentation sites into local Markdown/JSONL corpora and lets agents read pages, run crawls, check freshness, and diff changes with zero network access at read time. Single static binary, no CGO, Apache-2.0.

Enables full-text search and paginated retrieval of indexed documentation (PDFs, Markdown, text) through MCP tools, with filtering by category and file.

Enables extracting clean, structured markdown from any URL—stripping nav, ads, and scripts—for RAG pipelines and AI research agents, with pay-per-call micropayments via x402.

A CLI tool and MCP server that turns markdown documentation into a searchable, queryable knowledge base.

Enables searching a knowledge base and asking grounded questions with hybrid retrieval, reranking, and cited answers.

Enables conversational queries about a GitHub user's profile, using lazy indexing and tool calls to retrieve repository info and file contents, with cached results for efficiency.

Local RAG system for Claude Code with hybrid search (semantic + BM25), cross-encoder reranking, markdown-aware chunking, and 12 MCP tools. Zero external servers, pure ONNX in-process.

Enables a language model to query a document index through callable tools: ranked passage search, reading a chunk with its neighbours or a full document by id, index statistics, and sourced generated answers. The tools chain together, letting a model search, then read around the best chunk ids it received.

Provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.

Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.

A lightweight knowledge base MCP server that enables full-text search and retrieval of markdown documents from indexed sites using Orama BM25.