10 件の#retrieval MCP サーバー & クライアント

Local-first code retrieval for AI agents — cuts codebase context from tens of thousands of tokens to a few hundred, with zero hallucinated file paths.

Cognitive memory system for AI agents with 129 MCP tools. Persistent hierarchical memory, emotional recall, knowledge graphs, spreading activation, hybrid retrieval (BM25+RRF), metacognition, goal tracking, spaced repetition, dream consolidation, and more.

PinRAG is a retrieval-augmented generation (RAG) MCP server built with LangChain and Chroma. Index PDFs, plain text, Discord exports, YouTube transcripts, and GitHub repositories, then ask questions in Cursor, VS Code (Copilot), or any MCP-capable client. Answers include citation

AccInt is a local Work Model and MCP server for persistent scored agent memory, retrieval, commitments, browser/runtime observations, and outcome-based learning across coding agents.

Lochless

Lochless

Every match, not the top 10. Lochless is a hosted text index for LLM apps and agents. Send raw text through the API, then ask in plain English. It reads the documents in scope, up to a read limit you set, and returns eve

FetchGate

MoAz06

The agent only answers from a page it actually read.

Retrieve The Forgotten Memory

roomi-fields

The open retrieval layer for AI coding agents. Indexes code, docs, legal, research, data — 15 parsers, FTS5 + semantic search, knowledge graph. Serves surgical context via MCP. Open source, local, free.

Forge

VoxellInc

Forge is Voxell's hosted text-embedding API. This MCP server exposes two tools — embed (turn text into vectors) and list_models — so any MCP-compatible agent can generate embeddings for semantic search, RAG, clustering, and dedup.

MCP server for Voyage AI embeddings, reranking, and MongoDB Atlas Vector Search. Provides 11 tools for semantic search, document ingestion, cost estimation, and model exploration. Full RAG pipeline: chunk, embed, vector search, and rerank from any MCP client.