Skip to content

S3 Documentation MCP

AI-Powered Documentation Search
Transform your S3 docs into intelligent, context-aware answers

💬 Claude + S3 Doc MCP

🟢 Connected
👤
How do I configure the S3 MCP server?
🚧 Work in Progress✓ Open Source⚡ MIT License

Connect your LLM (Claude, Cursor, GPT) to S3-stored documentation for intelligent, RAG-powered answers. No complex infrastructure. No heavy dependencies.

🧠 ⚡ 📚

Semantic Search • Vector Embeddings • Real-time Sync

Built for developers who value simplicity and performance

🪶 Zero Dependencies

File-based vector storage with HNSWLib. No databases, no cloud services. Just simple, powerful RAG.

🏠 Your Data, Your Rules

Run embeddings locally with Ollama (free, private) or use OpenAI (cloud, high-accuracy). Switch anytime.

💾 Simple as Files

Vector indices are just files on disk. Easy to backup, version, and debug. No black boxes.

🔌 Universal S3

AWS S3, MinIO, Scaleway, Cloudflare R2, DigitalOcean… If it speaks S3, it works.


Terminal window
# 1. Pull Ollama model (local embeddings)
ollama pull nomic-embed-text
# 2. Configure S3 credentials
cp env.example .env # Add your S3 credentials
# 3. Run the server
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

That’s it! Your MCP server is now running on http://localhost:3000



For Developers

Dead simple to deploy

Works with Docker or Node.js. No Kubernetes, no cloud complexity. Just docker run and you’re done.

For Privacy-First Teams

100% offline capable

Use Ollama for completely local operation. Your docs never leave your infrastructure.

For Scale

Start small, scale smart

Free Ollama for dev → OpenAI for production. No vendor lock-in, no rewrites.

For Any S3 Storage

Universal compatibility

AWS, MinIO, Cloudflare R2, Scaleway… Works with any S3-compatible storage.


The Challenge

Your customers ask the same questions repeatedly. Support team searches through 500+ markdown files manually. Slow. Inefficient. Frustrating.

The Solution

📄 Docs on S3🔍 Index with MCP💬 Claude/Cursor

✨ Instant intelligent answers with sources

The Result

✅ Support queries answered in seconds, not minutes
Exact documentation references with every answer
✅ Team efficiency up 300%


  1. search_documentation

    Semantic search across all docs. Returns relevant chunks with similarity scores and sources.

  2. refresh_index

    Sync your vector index with S3. Incremental or full reindex on demand.

  3. get_full_document

    Retrieve complete files by S3 key. Perfect for viewing full context after search.



Ready to Transform Your Docs?

Join developers building AI-powered documentation systems in minutes, not months.

✓ MIT Licensed✓ Open Source✓ Free Forever✓ Community Support