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
NYTimes Article Search MCP Server is a small TypeScript Model Context Protocol server that puts New York Times article search behind one tool. That tool, search_articles, takes a required keyword parameter and returns articles from the last thirty days, each with its title, abstract, URL, publication date and author. The README presents the project as a demonstration of core MCP concepts as much as a utility: it shows how to expose a third-party HTTP API as a tool and how to wire the result into a client. Access to the New York Times API requires a key, supplied as the NYTIMES_API_KEY environment variable, either in a .env file at the project root for local runs or in the env block of the client configuration. Installation is either automatic through Smithery, which writes the Claude Desktop entry with a single npx command, or manual by adding a server entry that runs node against the built index.js, with the paths for the macOS and Windows configuration files documented. Development follows the usual Node cycle: npm install for dependencies, npm run build to compile and npm run watch to rebuild on change. Because MCP servers speak over stdio, which makes ordinary debugging awkward, the README recommends the MCP Inspector and exposes it as npm run inspector, which prints a browser URL for the debugging tools. After building, the server can also be started directly with node against the build output, at which point it waits for MCP requests on standard input. The project is MIT licensed. It suits anyone who wants an assistant to pull recent news coverage on a topic into a conversation, and it doubles as a compact reference for building a single-tool MCP server around a REST API.
https://github.com/angheljf/nyt
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.
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.
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.
World Monitor is an AI-powered, real-time global intelligence dashboard aggregating news and monitoring geopolitical and infrastructure data for unified situational awareness.
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.
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...
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...
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.