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
loopwork/iMCP
iMCP is a macOS application designed to serve as a Model Context Protocol (MCP) server, enabling AI clients to access and manage a variety of personal data services on a user's device. It acts as a bridge between AI clients and macOS native services such as Messages, Contacts, Calendar, Location, Maps, Reminders, and Weather, allowing these clients to interact with personal data securely and efficiently through the MCP framework. The app provides a user-friendly interface for managing permissions and activating services, ensuring that users have full control over what data is accessible. Each service can be toggled on or off, with permissions managed through standard macOS security dialogs, emphasizing privacy and user consent. iMCP integrates seamlessly with AI clients like Claude Desktop, facilitating enhanced AI interactions by providing real-time access to personal contextual data. This integration allows AI to answer personalized queries, manage calendar events, send messages, and provide location-based information without requiring manual data sharing during conversations. Technically, iMCP bundles a command-line executable, imcp-server, which handles MCP server operations using standard input/output communication. The app and CLI communicate over the local network using Bonjour for automatic discovery, ensuring smooth interaction between components. The project also contributed to the development of the official Swift SDK for MCP servers and clients, highlighting its role in advancing the MCP ecosystem. Overall, iMCP is a powerful tool that connects digital life with AI by leveraging the Model Context Protocol to provide secure, user-controlled access to personal data services on macOS.
https://github.com/loopwork/iMCP
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.