RAGStack-Lambda MCP Server

$npx -y @hatmanstack/ragstack-lambda
README.md

Serverless document and media processing with AI chat

. Upload documents, images, video, and audio — extract text with OCR or transcription — query using Amazon Bedrock.

Tools (3)

upload_documentUpload documents, images, video, or audio for processing.
query_contentQuery processed content using Amazon Bedrock.
extract_textPerform OCR or transcription on uploaded media files.

Environment Variables

AWS_REGIONrequiredThe AWS region where Bedrock and Lambda are deployed
AWS_ACCESS_KEY_IDrequiredAWS access key for authentication
AWS_SECRET_ACCESS_KEYrequiredAWS secret key for authentication

Configuration

claude_desktop_config.json
{
  "mcpServers": {
    "ragstack-lambda": {
      "command": "npx",
      "args": ["-y", "@hatmanstack/ragstack-lambda"],
      "env": {
        "AWS_REGION": "us-east-1",
        "AWS_ACCESS_KEY_ID": "<your-key>",
        "AWS_SECRET_ACCESS_KEY": "<your-secret>"
      }
    }
  }
}

Try it

Upload this PDF and summarize its main points using RAGStack.
Transcribe this audio file and then ask Bedrock to identify the action items.
Perform OCR on this image and search the text for any mentions of invoice numbers.
Query my uploaded documents to find the project deadline mentioned in the meeting notes.

Frequently Asked Questions

How do I install RAGStack-Lambda?

Install RAGStack-Lambda by running: npx -y @hatmanstack/ragstack-lambda

What MCP clients work with RAGStack-Lambda?

RAGStack-Lambda works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Use RAGStack-Lambda with Conare

Manage MCP servers visually, upload persistent context, and never start from zero with Claude Code & Codex.

Try Free