Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.
1
Prepare the server locally
Run this once before adding it to Claude Code.
git clone https://github.com/LuizDoPc/mcp-rag
cd mcp-ragThen follow the repository README for any remaining dependency or build steps.
2
Register it in Claude Code
claude mcp add mcp-rag -- node /path/to/dist/index.jsReplace any placeholder paths in the command with the real path on your machine.
3
Make your agent remember this setup
mcp-rag's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Local processing with no external API costs
- Supports PDF, Markdown, and TXT file formats
- Configurable chunk size and overlap for context optimization
- Semantic search using nomic-embed-text model via Ollama
- Seamless integration with MCP-compatible clients like Cursor
Tools 4
ingest_docsIngest documents from a directorysearchSearch for relevant document chunksget_chunkRetrieve a specific chunk by IDrefresh_indexClear and refresh the entire indexTry it
→Search for information about project requirements in my local documents.
→Ingest all new files from the ./docs folder into the vector database.
→Find the most relevant chunks for the query 'how to configure the server'.
→Refresh the document index to include recent changes.
Original README from LuizDoPc/mcp-rag
MCP RAG Server
A Model Context Protocol (MCP) server that provides RAG (Retrieval-Augmented Generation) functionality using local embeddings via Ollama and Chroma vector database.
Features
- Local Processing: No external API costs - runs entirely locally
- Multiple Formats: Supports PDF, Markdown, and TXT files
- Smart Chunking: Configurable chunk size with overlap for better context
- Vector Search: Semantic search using nomic-embed-text model via Ollama
- MCP Integration: Works seamlessly with Cursor and other MCP clients
Prerequisites
- Node.js (v18 or higher)
- Docker (for ChromaDB)
- Homebrew (for Ollama on macOS)
🚀 Quick Start
Setup (one time)
npm run setup
This will:
- Start Ollama and install nomic-embed-text model
- Start ChromaDB with Docker
- Build the project
- Ingest documents from
./docs
Development
# Start MCP server
npm run dev
# Ingest new documents
npm run ingest
Stop Services
npm run stop
Configuration
The server uses a config.json file for configuration:
{
"documentsPath": "./docs",
"chunkSize": 1000,
"chunkOverlap": 200,
"ollamaUrl": "http://localhost:11434",
"embeddingModel": "nomic-embed-text",
"chromaUrl": "http://localhost:8001",
"collectionName": "rag_documents",
"mcpServer": {
"name": "mcp-rag-server",
"version": "1.0.0"
}
}
MCP Tools
ingest_docs({path?})- Ingest documents from a directorysearch({query, k?})- Search for relevant document chunksget_chunk({id})- Retrieve a specific chunk by IDrefresh_index()- Clear and refresh the entire index
MCP Resources
rag://collection/summary- Collection statistics and metadatarag://doc/<filename>#<chunk_id>- Individual document chunks
Configure in Cursor
Add to your Cursor MCP settings:
{
"mcpServers": {
"rag-server": {
"command": "node",
"args": ["/Users/luizsoares/Documents/buildaz/mcp_rag/dist/index.js"],
"env": {}
}
}
}
Available Scripts
npm run setup- Complete setup (Ollama + ChromaDB + build + ingest)npm run dev- Start MCP server in development modenpm run ingest- Ingest documentsnpm run build- Build the projectnpm run test- Run testsnpm run stop- Stop all services
Troubleshooting
- Ollama Connection Issues: Ensure Ollama is running on the configured URL
- Model Not Found: Run
ollama pull nomic-embed-textto install the embedding model - Docker Issues: Ensure Docker is running and accessible