S3 Documentation MCP Server

S3 Documentation MCP server exists for a simple reason — assistants are far more useful when they can act on S3 Documentation directly instead of describing what you should do. HTTP MCP server for S3 documentation with RAG using HNSWLib and Ollama.

What you get

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

It's the sweet spot between simplicity and performance for RAG applications.

• 🔌 Universal S3: AWS S3, MinIO, Scaleway, DigitalOcean Spaces, Cloudflare R2, Wasabi..
• 🧠 Flexible Embeddings:
• Ollama — (nomic-embed-text) - Local, free, offline-capable
• OpenAI — (text-embedding-3-small, text-embedding-3-large) - Cloud-based, high-accuracy, multilingual
• 🔄 Smart Sync: Incremental updates via ETag comparison + automatic full sync on empty vector store
• ⚡ Fast Search: HNSWLib vector index with cosine similarity

What the assistant can call

Once S3 Documentation is connected, these are the calls the assistant has available:

• Cursor — The Cursor tool exposed by this server
• search_documentation — Returns relevant document chunks with similarity scores and sources
• refresh_index — Synchronizes the documentation index with S3, detecting new, modified, or deleted files
• get_full_document — Retrieves the complete content of a Markdown file from S3 along with metadata: - Full S3 key: The document's S3 identifier - **Complete Markdown

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Configuration and credentials

You will need 5 environment variables: OLLAMA_BASE_URL, S3_ACCESS_KEY_ID, S3_SECRET_ACCESS_KEY, OPENAI_API_KEY, MCP_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

• 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.)

Choosing this one

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. S3 Documentation's toolset — Cursor, search_documentation, refresh_index and 1 more — is a fair guide to whether it matches your workflow. It is maintained by yoanbernabeu; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against S3 Documentation's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Before you rely on it

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the s3 documentation mcp server does with a few real requests.