rag-mcp

A RAG-over-docs MCP server: ingest text into collections, then let any LLM agent semantically search it. Backed by PostgreSQL + pgvector, embeddings via any OpenAI-compatible endpoint (OpenAI, Azure, or a local Ollama / llama.cpp server).

RAG is split the MCP-native way — this server owns retrieval (chunk → embed → store → cosine search); the calling model owns generation. Point Claude, ChatGPT, Cursor, or any MCP client at it and answers get grounded in your docs.

Tools

Related MCP server: RAG-MCP Knowledge Base Server

Quickstart

# 1. Start Postgres + pgvector and the server
cp .env.example .env         # set EMBEDDINGS_API_KEY
docker compose up -d --build

# — or run locally over stdio (e.g. for Claude Desktop) —
uv pip install --system .
docker compose up -d db      # just the database
EMBEDDINGS_API_KEY=sk-... rag-mcp

Add to an MCP client (stdio):

{ "mcpServers": { "rag": { "command": "rag-mcp",
  "env": { "EMBEDDINGS_API_KEY": "sk-...",
           "DATABASE_URL": "postgresql://postgres:postgres@localhost:5432/rag" } } } }

Deployment overrides

For host-specific tweaks (e.g. dropping public port bindings on a server where only the internal Docker network should reach Postgres), copy docker-compose.override.yml.example to docker-compose.override.yml — it's gitignored and loaded automatically by docker compose. Don't hand-edit the tracked docker-compose.yml or hide local changes with git update-index --skip-worktree; either desyncs git status/git diff from what's actually deployed and can silently block fast-forward merges of upstream fixes.

Configuration

All via environment (see .env.example): DATABASE_URL, EMBEDDINGS_API_BASE / EMBEDDINGS_API_KEY / EMBEDDINGS_MODEL, EMBED_DIM (must match your model's dimension — 1536 for text-embedding-3-small), CHUNK_SIZE, CHUNK_OVERLAP, and MCP_TRANSPORT (stdio | http).

How it works

ingest_text splits text on natural boundaries with overlap, embeds each chunk, and stores it in a chunks table with a vector(EMBED_DIM) column and an ivfflat cosine index. search embeds the query and returns the nearest chunks by cosine distance (<=>). Everything is namespaced by collection.

License

Copyright © 2026 Next Level Management Advisors, LLC.

Licensed under the GNU Affero General Public License v3.0 (AGPL-3.0) — see LICENSE. If you run a modified version over a network, the AGPL requires you to make your modified source available to its users.

Commercial licensing: to use this in a closed-source or commercial product, or to host a modified version without publishing your source, a commercial license is available — contact forrest@nlma.io.