"RAG (Retrieval-Augmented Generation) MCP Integration for ChatGPT" matching MCP servers:

Enables hybrid retrieval-augmented generation with semantic and keyword search over documents, supporting multiple formats and providing MCP integration for Claude Desktop.

A Model Context Protocol (MCP) server with Retrieval-Augmented Generation (RAG) for answering questions about imaginary SuperNova documentation. Enables semantic search over documentation using HuggingFace embeddings.

Enables local retrieval-augmented generation document search for Cline by providing semantic search over indexed files, listing indexed sources, and reporting index status through MCP tools.

Enables AI agents to search private GitHub Pages by authenticating in a dedicated browser and retrieving indexed sections from a local SQLite database, with support for multiple sites and languages.

Provides read-only RAG retrieval, document access, source auditing, status, and health checks for CUMCM optimization and decision modeling contexts.

A BM25-based MCP server that enables document search and retrieval across structured domains of knowledge content, allowing Claude to search and reference documentation when answering questions.

Retrieval-Augmented Generation system serving LangGraph documentation through the Model Context Protocol, enabling semantic search and context-aware responses.

Enables coding agents to retrieve relevant sections from a repository's declared documentation scope using hybrid vector and full-text search, with incremental indexing.

Enables cited, revision-aware retrieval over real IETF RFC chunks with zero LLM in the answer path, including graph-based supersession resolution and relationship queries via MCP tools.

Enables agents to diagnose failing API calls from request logs and customer tickets, identifying root causes with cited request IDs and returning escalation and paging flags. It also exposes runbook lookups and a cause catalog, with secrets redacted in all output.

MCP server exposing a RAG knowledge base as read-only tools (search_knowledge_base, ask_knowledge_base, kb_stats, kb_diagnostic) for AI clients like Claude Desktop and Cursor, enabling token-efficient document retrieval and Q&A.

Provides read-only MCP tools for hybrid semantic and keyword search over locally indexed PDF documentation, with citations and context retrieval for LLM agents.

An MCP server that enables users to query Kedro framework documentation using retrieval-augmented generation. It builds a local knowledge base from documentation files to help users navigate and apply Kedro's data science pipeline framework.

Standalone MCP server exposing agentic-RAG tools (hybrid search, article retrieval, category listing) over a pgvector-backed knowledge base with bearer-token auth, designed for deployment on Render.

A RAG MCP server that enables retrieval-augmented question answering over PyTorch documentation, with hybrid search (FAISS+Chroma, BM25) and source-cited responses from DeepSeek.

Enables AI agents to connect local knowledge bases, preview and index selected directories, search for traceable snippets with source metadata, and read indexed document versions through MCP tools.

Provides read-only retrieval of STM32 datasheet and reference manual content with exact citations, page numbers, register details, and source hashes so Claude can answer questions or generate code from verified evidence.

Enables question answering over technical documents (Markdown, TXT, PDF) using hybrid retrieval (vector + lexical) with cited sources and audit logging, fully locally with optional cloud fallback.

Automatically crawls documentation websites, converts them to organized markdown files, and generates condensed cheat sheets. Intelligently categorizes content into tools/APIs and provides local-first access to downloaded documentation.

Enables ChatGPT or other MCP clients to consult explicitly configured local repositories and worktrees, search and read UTF-8 text, optionally access authorized Codex conversation history, and write new Markdown candidates only after confirmed preview.