S3 Documentation MCP Server

A lightweight Model Context Protocol (MCP) server that brings RAG (Retrieval-Augmented Generation) capabilities to your LLM over Markdown documentation stored on S3.

Built for simplicity:

• 🪶 Lightweight Stack: No heavy dependencies or cloud services
• 🏠 Flexible Embeddings: Choose between Ollama (local, free) or OpenAI (cloud, high-accuracy)
• 💾 File-based Storage: Vector indices stored as simple files (HNSWLib)
• 🔌 S3-Compatible: Works with any S3-compatible storage (AWS, MinIO, Scaleway, Cloudflare R2...)

[!IMPORTANT]
🚧 This project is a work in progress. APIs and behavior may change at any time, and backward compatibility is not ensured. Not suitable for production.

Requirements

• Embedding Provider (choose one):
  • Ollama (recommended for local/offline use) with the nomic-embed-text model
  • OpenAI API Key (for cloud-based embeddings)
• Node.js >= 18 (if running from source) OR Docker (recommended)
• S3-compatible storage (AWS S3, MinIO, Scaleway, Cloudflare R2, etc.)

Use Cases

• 📚 Product Documentation: Let Claude/Cursor/etc answer from your docs
• 🏢 Internal Wiki: AI-powered company knowledge search
• 📖 API Docs: Help developers find API information
• 🎓 Educational Content: Build AI tutors with course materials

Quick Start

With Docker (Recommended)

# 1. Prerequisites
# Install Ollama from https://ollama.ai
ollama pull nomic-embed-text

# 2. Configure
cp env.example .env  # Add your S3 credentials

# 3. Run
docker run -d \
  --name s3-doc-mcp \
  -p 3000:3000 \
  --env-file .env \
  -e OLLAMA_BASE_URL=http://host.docker.internal:11434 \
  -v $(pwd)/data:/app/data \
  yoanbernabeu/s3-doc-mcp:latest

Or use Docker Compose (Local Build):

docker compose up -d

From Source

# 1. Prerequisites
# Install Ollama from https://ollama.ai
ollama pull nomic-embed-text

# 2. Install & Run
npm install
cp env.example .env  # Configure your S3 credentials
npm run build && npm start

# 3. For local development
npm run dev

Your MCP server is now running on http://localhost:3000

Connect to MCP Clients

Once your server is running, you need to configure your MCP client to connect to it.

Cursor

Edit your ~/.cursor/mcp.json file and add:

{
  "mcpServers": {
    "doc": {
        "type": "streamable-http",
        "url": "http://127.0.0.1:3000/mcp",
        "note": "S3 Documentation RAG Server"
    }
  }
}

Claude Desktop

Edit your Claude Desktop configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "doc": {
        "type": "streamable-http",
        "url": "http://127.0.0.1:3000/mcp",
        "note": "S3 Documentation RAG Server"
    }
  }
}

Restart your MCP client, and you should now see:

• 3 MCP Tools: search_documentation, refresh_index, get_full_document
• MCP Resources: Full list of indexed documenta

... View full README on GitHub