Ragstack

Name: Ragstack
Author: hatmanstack

by hatmanstackcommunityv0.1.4

This MCP server enables serverless document and media processing with AI chat, allowing users to upload various file types, extract text, and query using Amazon Bedrock or AI assistants.

From the registry: Search, chat, upload, and scrape a serverless RAGStack knowledge base on AWS.

GitHub Repository

Install & configure

Prerequisites

required
Deploy RAGStack to AWS
RAGStack is a serverless AWS application. Deploy via AWS Marketplace one-click or from source using SAM CLI.
https://aws.amazon.com/marketplace/pp/prodview-5afdiw2zrht6o
required
Get RAGStack API key
Get your API key from the RAGStack Dashboard under Settings

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `ragstack` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Deploy RAGStack to AWS** — RAGStack is a serverless AWS application. Deploy via AWS Marketplace one-click or from source using SAM CLI. (https://aws.amazon.com/marketplace/pp/prodview-5afdiw2zrht6o)
- **Get RAGStack API key** — Get your API key from the RAGStack Dashboard under Settings

Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["ragstack-mcp"]
- required environment variables:
  - `RAGSTACK_GRAPHQL_ENDPOINT`: Your RAGStack GraphQL endpoint URL (example: `<your-graphql-endpoint>`)
  - `RAGSTACK_API_KEY`: Your RAGStack API key from the dashboard (example: `<your-api-key>`)

Note: Serverless document/media RAG on AWS (Lambda, S3, DynamoDB, Bedrock). Supports PDF, images, video/audio, and web scraping. MCP package: pip install ragstack-mcp or uvx ragstack-mcp.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Serverless document/media RAG on AWS (Lambda, S3, DynamoDB, Bedrock). Supports PDF, images, video/audio, and web scraping. MCP package: pip install ragstack-mcp or uvx ragstack-mcp.