yogthos/Matryoshka
MCP server for token-efficient large document analysis via the use of REPL state
This tool helps you analyze extremely large documents, like extensive log files or reports, to quickly find specific information without getting bogged down by the sheer size. You provide a natural language question and a document, and it extracts the relevant data, presenting it as a clear answer. This is perfect for operations engineers, data analysts, or anyone who needs to extract precise insights from very long text files.
109 stars.
Use this if you need to extract specific answers or aggregate data from documents that are too large for standard AI tools to process effectively, and you want to maintain accuracy across the entire file.
Not ideal if your documents are short, or you need to perform highly nuanced, open-ended creative tasks rather than structured data extraction or question answering.
Stars
109
Forks
12
Language
TypeScript
License
—
Category
Last pushed
Mar 04, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/yogthos/Matryoshka"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DMontgomery40/deepseek-mcp-server
Model Context Protocol server for DeepSeek's advanced language models
upstash/context7
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
graphlit/graphlit-mcp-server
Model Context Protocol (MCP) Server for Graphlit Platform
dvcrn/mcp-server-siri-shortcuts
MCP for calling Siri Shorcuts from LLMs
rawveg/ollama-mcp
An MCP Server for Ollama