Ragstack Lambda MCP Server

Serverless OCR-to-Knowledge Base pipeline on AWS

Local serverstdioPython

What is the Ragstack Lambda MCP server?

Serverless OCR-to-Knowledge Base pipeline on AWS. That is what the ragstack lambda mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

Serverless document and media processing with AI chat. Scale-to-zero architecture — no vector database fees, no idle costs. Upload documents, images, video, and audio — extract text with OCR or transcription — query using Amazon Bedrock or your AI assistant via MCP.

  • ☁️ Fully serverless architecture (Lambda, Step Functions, S3, DynamoDB)
  • 🧠 NEW Amazon Nova multimodal embeddings for text and image vectorization
  • 📄 Document processing & vectorization (PDF, images, Office docs, HTML, CSV, JSON, XML, EML, EPUB) → stored in managed knowledge base
  • 🎬 NEW Video/audio processing - transcribe speech with AWS Transcribe, searchable by timestamp
  • 💬 AI chat with retrieval-augmented context and source attribution
  • 📎 Collapsible source citations with optional document downloads

The tools it exposes

The server publishes 3 tools. What each one is for:

  • Documents — Upload documents in various formats. Auto-detection routes to optimal processor:
  • Images — Upload JPG, PNG, GIF, WebP with captions. Both visual content and caption text are searchable
  • Chat — Ask questions about your content. Sources show where answers came from

What it needs from you

Configuration is passed through the environment: RAGSTACK_GRAPHQL_ENDPOINT, RAGSTACK_API_KEY, YOUR_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

for on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

This sits in the cloud and infrastructure group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Ragstack Lambda's toolset — Documents, Images, Chat — is a fair guide to whether it matches your workflow. It is maintained by hatmanstack; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • 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.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
DocumentsUpload documents in various formats. Auto-detection routes to optimal processor:
ImagesUpload JPG, PNG, GIF, WebP with captions. Both visual content and caption text are searchable.
ChatAsk questions about your content. Sources show where answers came from.

How to install the Ragstack Lambda MCP server

{
  "mcpServers": {
    "ragstack-lambda": {
      "command": "uvx",
      "args": ["for"],
      "env": {
        "RAGSTACK_GRAPHQL_ENDPOINT": "your-value",
        "RAGSTACK_API_KEY": "your-value",
        "YOUR_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
RAGSTACK_GRAPHQL_ENDPOINTConfiguration value read at startup.Optional
RAGSTACK_API_KEYCredential the server authenticates with.Yes
YOUR_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Ragstack Lambda to Documents.
  • Use Ragstack Lambda to Images.
  • Use Ragstack Lambda to Chat.

Frequently asked questions

It connects Ragstack Lambda to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (Documents, Images, Chat) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Ragstack Lambda directly.