SkillTide Submit
Official description7 sourcesMCP servers8d ago
HatmanStack/ragstack-mcp

HatmanStack/ragstack-mcp

๐Ÿ โ˜๏ธ ๐ŸŽ ๐ŸชŸ ๐Ÿง - Access RAGStack serverless knowledge bases on AWS: search, chat with AI answers, uploadโ€ฆ
View on GitHub โ†—Direct link ยท no redirect page
Official description๐Ÿ โ˜๏ธ ๐ŸŽ ๐ŸชŸ ๐Ÿง - Access RAGStack serverless knowledge bases on AWS: search, chat with AI answers, upload documents and media, scrape websites and analyze metadata.
Config template (adjust for your client)
claude mcp add ragstack-lambda -- npx -y ragstack-lambda
A pasteable skeleton generated from the repository name. Check the project README for the exact package and arguments.
Star count
25 โ˜… ยท HatmanStack/RAGStack-Lambda ยท read from the repository page ยท (checked 2026-10-16 20:00:20)
Source
collected from the punkpeye/awesome-mcp-servers list ยท type: MCP server
Harvest history
first seen 2026-10-09 ยท last seen 2026-10-16 ยท seen 32ร— ยท listed by 7 sources
Score
score 703 ยท 25 โ˜… ยท 7 sources ยท mcp
FAQ (answers come from our records)
How do I install it?
We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.
Who is it for?
We filed it under these tags: MCP ๆœๅŠก. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository HatmanStack/RAGStack-Lambda๏ผ›first catalogued 2026-10-09๏ผ›last seen 2026-10-16ใ€‚There is no official certification or quality rating here โ€” we record sources and dates only.
Third-party quality signals

Serverless document and media processing with AI chat. Scale-to-zero architectur

ไปฅไธ‹ๆ‘˜ๅฝ•่‡ช่ฏฅไป“ๅบ“็š„ README๏ผˆ็‰‡ๆฎต๏ผ‰ ยท ๅœจ GitHub ่ฏปๅฎŒๆ•ด README โ†’

QUESTIONS?
Features
- โ˜๏ธ Fully serverless architecture (Lambda, Step Functions, S3, DynamoDB)
- ๐Ÿง  **NEW** Amazon Nova multimodal embeddings for text and image vectorization
- ๐Ÿ“„ Document processing & vectorization (PDF, images, Office docs, HTML, CSV, JSON, XML, EML, EPUB) โ†’ stored in managed knowledge base
- ๐ŸŽฌ **NEW** Video/audio processing - transcribe speech with AWS Transcribe, searchable by timestamp
- ๐Ÿ’ฌ AI chat with retrieval-augmented context and source attribution
- ๐Ÿ“Ž Collapsible source citations with optional document downloads
- โฑ๏ธ **NEW** Media sources with timestamp links - click to play at exact position
- ๐Ÿ” Metadata filtering - auto-discover document metadata and filter search results
- ๐ŸŽฏ Relevancy boost for filtered results - prioritize matches from metadata filters
- ๐Ÿ”„ Knowledge Base reindex - regenerate metadata for existing documents with updated settings
- ๐Ÿ—‘๏ธ Document management - reprocess, reindex, or delete documents from the dashboard
- ๐ŸŒ Web component for any framework (React, Vue, Angular, Svelte)
- ๐Ÿš€ One-click deploy
- ๐Ÿ’ฐ $7-10/month (1000 docs, Textract + Haiku)
Live Demo
| Environment | URL | Credentials |
|-------------|-----|-------------|
| **Base Pipeline** | dhrmkxyt1t9pb.cloudfront.net | guest@hatstack.fun / Guest@123 |
| **Project Showcase** | showcase-htt.hatstack.fun | Login as guest |
> **Base Pipeline**: The core document processing tool - upload, OCR, and query documents.
>
> **Project Showcase**: See RAGStack powering a real application.
Quick Start
Option 1: One-Click Deploy (AWS Marketplace)
**REPO IS IN ACTIVE DEVELOPMENT AND WILL CHANGE OFTEN**
Deploy directly from the AWS Console - no local setup required:
1. Subscribe to RAGStack on AWS Marketplace (free, not required - If subscribed Lambda roles auto-accept Bedrock model agreements on first invocation)
2. Click here to deploy
3. Enter a stack name (**lowercase only**, e.g., "my-docs") and your admin email
4. Click **Create Stack** (deployment takes ~10 minutes)
**After deployment:**
- Check your email for the temporary password (from Cognito)
- Go to CloudFormation โ†’ your stack โ†’ **Outputs** tab to find the Dashboard URL (UIUrl)
Option 2: Deploy from Source
For customization or development:
**Prerequisites:**
- AWS Account with admin access
- Python 3.13+, Node.js 24+
- uv (Python package manager)
- AWS CLI, SAM CLI (configured)
- Docker (for Lambda layer builds)
Option 3: Nested Stack Deployment
Deploy RAGStack as part of a larger CloudFormation stack. See Nested Stack Deployment Guide for details.
**Quick example:**
Web Component Integration
See RAGSTACK_CHAT.md for web component integration guide.
API Access
**Server-side integrations** use API key authentication. Get your key from Dashboard โ†’ Settings.
**Web component** uses IAM auth (no API key needed - handled automatically).
Each UI tab shows server-side API examples in an expandable section.
MCP Server (AI Assistant Integration)
Use your knowledge base directly in Claude Desktop, Cursor, VS Code, Amazon Q CLI, and other MCP-compatible tools.
Add to your AI assistant's MCP config:
Then ask naturally: *"Search my knowledge base for authentication docs"*
See MCP Server docs for full setup instructions.
Source
awesome ยท https://github.com/HatmanStack/RAGStack-Lambda/tree/main/src/ragstack-
Browse by field
MCP servers
Traction
25 โ˜…
added
yesterday

More in MCP servers

All 5,525 in MCP servers โ†’

Filed under

Every tag opens the full list for that filter. Counts are the live catalogue figures.

Browse all fields โ†’

โ† Back to index