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
This package is an MCP server that gives an LLM structured access to information about a single job candidate. The README states plainly that it is meant to be used as a library embedded in another application rather than as a standalone service, and that the bundled startup paths exist for demonstration and testing. The server publishes the same candidate data through two surfaces. As MCP resources it serves candidate-info URIs for the resume text, the resume URL, the LinkedIn profile URL, the GitHub profile URL, the personal website URL, and the text content of that website. As tools it offers matching getters for each of those fields, so clients that do not consume resources can still reach the data, plus a contact tool that sends an email to the candidate, which requires Mailgun configuration to be present. Configuration is split in two. A server config carries the server name and version and the Mailgun API key, domain and contact address. A candidate config carries the person specific values such as name, email and resume URL. Where those values come from is left to the host application: the README suggests hard-coding them or loading them from a JSON Resume URL at start-up. A createServer factory combines the two configs into a server instance that is then attached to a transport. The documentation shows three deployments: stdio for local processes, a stateless streamable HTTP setup on Express where a fresh server and transport are created per request to avoid request id collisions between concurrent clients, and a shorter variant using the express-mcp-handler package to generate that binding. It is aimed at developers building a personal site or hiring tool that should answer agent queries about a candidate.
https://github.com/jhgaylor/node-candidate-mcp-server
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.