microsoft/markitdown
MarkItDown is a Python tool that converts various file formats into Markdown and integrates with LLM applications via an MCP server for enhanced text analysis and document processing.
Awesome MCP › Other MCP Servers
deadletterq/mcp-opennutrition
mcp-opennutrition is a Model Context Protocol server written in TypeScript that gives an LLM assistant access to the OpenNutrition food database, a dataset of more than 300,000 food items assembled from authoritative public sources including the USDA database, the Canadian Nutrient File, the Danish FRIDA database and AUSNUT. The README frames the dataset as an answer to fragmented nutrition data: unlike user-generated food databases with inconsistent entries, or commercial databases with restrictive licensing, OpenNutrition is meant to be transparent and freely usable by developers and researchers. The server exposes four tools. Search by name finds foods by name, brand or partial match. Browse foods returns paginated lists of all available entries. Get by ID retrieves the full nutritional record for a known food identifier. Barcode lookup resolves an EAN-13 barcode to a food item. Records include macronutrients, vitamins and minerals. The recommended way to run it is Docker: the published deadletterq/mcp-opennutrition image is started with a port mapping and registered in the client configuration as a streamable-http endpoint. Building from source is also documented, with npm install and npm run build followed by an mcpServers entry pointing a node binary at build/index.js; the README notes the node version used to build must match the one configured. All data and query processing happen locally on the machine with no external API calls, which the author presents as both a privacy property and a latency benefit. It targets users of Claude, Cline and similar clients who want recipe, diet or nutrition calculations grounded in a real food database.
https://github.com/deadletterq/mcp-opennutrition
Also in Other MCP Servers
punkpeye/awesome-mcp-servers
A curated collection of Model Context Protocol (MCP) servers that enable AI models to securely interact with local and remote resources through standardized server implementations.
modelcontextprotocol/servers
The Model Context Protocol Servers repository offers reference implementations and third-party integrations that demonstrate how MCP enables Large Language Models to securely access and interact with diverse tools and data sources.
koala73/worldmonitor
World Monitor is an AI-powered, real-time global intelligence dashboard aggregating news and monitoring geopolitical and infrastructure data for unified situational awareness.
headroomlabs-ai/headroom
Headroom is a context compression layer for AI agents, reducing token usage by 60-95% while preserving accuracy, implemented as a library, proxy, and MCP server.
diegosouzapw/OmniRoute
OmniRoute is a free AI gateway that connects various AI tools and models from over 230 providers through a single endpoint, featuring token compression, smart auto-fallback, and support for Model C...
rohitg00/ai-engineering-from-scratch
This comprehensive curriculum teaches AI engineering from scratch, focusing on building AI algorithms, agents, and MCP servers hands-on, covering everything from mathematical foundations to autonom...
every-app/open-seo
Open source, self-hostable SEO platform that exposes its keyword, rank, backlink and site-audit data to AI agents through an MCP server and a set of companion agent skills.