"MCP with RAG capabilities" matching MCP servers:

A multi-agent Retrieval-Augmented Generation system exposed as an MCP server. Ask a question and a LangGraph pipeline plans the retrieval, pulls evidence from a pgvector knowledge base, optionally augments it with live web research, drafts a cited answer, and then self-critiques it for grounding — revising until the answer is supported by the sources.

A local MCP server that enables LLMs to securely search and read files within designated Google Drive folders. Supports Google Docs, Google Sheets, PDFs, and plain text with strict folder-scoping via service account authentication.

A hosted multimodal RAG MCP server that enables natural language queries over text and visual content (PDFs, images, etc.) with verifiable citations, easily run via npx with a Calypso API key.

Enables RAG over messy PDFs — extract, chunk, embed, and search scanned, multi-column, and table-heavy documents.

Enables ingestion and semantic search over text documents using PostgreSQL + pgvector and OpenAI-compatible embeddings, allowing any LLM agent to retrieve relevant chunks for grounded answers.

Searches local markdown files using TF-IDF retrieval and serves full documents as resources.

Enables natural-language and keyword search across Obsidian notes, returning reranked passages with provenance, and supports reading notes and incremental indexing.

Enables asking natural language questions about local videos, using Whisper transcription, ChromaDB vector storage, and Groq for timestamped answers via MCP.

"primitive" RAG-like web search model context protocol server that runs locally. ✨ no APIs ✨

Provides RAG tools with local vector retrieval and web fallback using Firecrawl, enabling document ingestion and querying through MCP stdio transport.

Provides AI assistants with progressive code intelligence to explore repository structure, find symbols, and assess the impact of changes using ast-grep.

Enables users to ask natural-language questions about a local folder's contents, including file names, sizes, and timestamps, with rollups by type and age and cleanup suggestions for stale or large files. It returns metadata only and cannot read, move, or delete files.

Read-only SQL MCP server for quantitative finance data (DuckDB) with stock quotes, financials, and historical K-lines, enabling cross-database JOIN queries.

MCP server that resolves postal/ZIP codes to place names, states, and coordinates using Zippopotam.us. Free, no API key required.

Enables real-time domain registration lookups via RDAP, including availability, expiration, and registrar details, with no API key required. Supports natural language queries like 'is example.com available?' or 'when does example.com expire?'.

Unified MCP server for Polish legal data, enabling search and retrieval across case law, legislation, company register, tax rulings, public procurement, and EU sources through four aggregated tools.

A Python-based MCP server that enables AI agents to query the Microsoft 365 Roadmap programmatically.

Fetches a URL and returns the main content as clean Markdown, using plain HTTP when possible and headless Chromium for JavaScript-rendered or bot-protected pages.

Composes arbitrary MCP tools using JavaScript, enabling discovery, composition, and execution of other MCP servers through a single 'exec' tool.

Enables AI assistants to perform Google searches with real, resolvable sources and transparent search terms.