Happy slice of mcp pizzaMCP.pizza

RAGStack-Lambda

MCP.Pizza Chef: HatmanStack

RAGStack-Lambda lets you upload documents, images, audio, and video to create a searchable knowledge base. It transcribes speech, extracts text, and uses AI chat to answer your questions with source links. You can use it inside apps like Claude Desktop, Cursor, and VS Code once set up. It requires deploying on AWS and some developer skills, but offers a powerful way to query your files with AI assistance.

Files/PDF
Other
Web/Research

Use This MCP server To

Upload PDFs and images to build a searchable knowledge base Ask my AI assistant questions about my uploaded documents Transcribe audio and video files and search their content by timestamp Filter search results by document metadata for precise answers Chat with AI that cites sources and lets me download original files Manage documents by reprocessing or deleting them from a dashboard

README

RAGStack-Lambda-app icon

Apache 2.0 License Python 3.13 React 19

AWS Lambda AWS Bedrock AWS Transcribe AWS S3 AWS DynamoDB AWS Cognito

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.

QUESTIONS? Deep WIKI

Features

  • ☁️ 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
  • ⏱️ NEW Media sources with timestamp links - click to play at exact position
  • 🔍 Metadata filtering - auto-discover document metadata and filter search results
  • 🎯 Relevancy boost for filtered results - prioritize matches from metadata filters
  • 🔄 Knowledge Base reindex - regenerate metadata for existing documents with updated settings
  • 🗑️ Document management - reprocess, reindex, or delete documents from the dashboard
  • 🌐 Web component for any framework (React, Vue, Angular, Svelte)
  • 🚀 One-click deploy
  • 💰 $7-10/month (1000 docs, Textract + Haiku)

Live Demo

RAGStack-Lambda FAQ

Can I use this to upload and search documents with AI chat?
Yes — you can upload PDFs, images, videos, and more, then ask your AI assistant questions with source links.
Can I use this to transcribe and search audio or video content?
Yes — it transcribes speech with timestamps, letting you search and jump to exact moments.
Which apps support RAGStack-Lambda?
It works with Claude Desktop, Cursor, and VS Code via MCP integration.
Do I need an AWS account or special keys?
Yes — setup requires AWS services and API keys; you must deploy it yourself or via AWS Marketplace.
How hard is it to set up?
Setup is developer-level, needing AWS knowledge, command line tools, and some coding.
Can I use this without coding?
There is a one-click AWS deploy option, but some cloud familiarity is helpful.