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
The project "homeassistant-mcp" is a Model Context Protocol (MCP) server designed specifically for Home Assistant, enabling natural language control and real-time management of smart home devices through integration with Language Learning Models (LLMs). It acts as a powerful bridge between a local Home Assistant instance and LLM applications, providing a comprehensive API for managing the entire Home Assistant ecosystem, including device control, system administration, automation management, and state monitoring. Key features include device control for a wide range of smart home devices such as lights, climate control, covers, switches, sensors, media players, fans, locks, vacuums, and cameras. The server supports real-time updates via Server-Sent Events (SSE), allowing instant state changes, monitoring of automation triggers and executions, and subscription to specific domains or entities. It also offers robust system management capabilities including add-on management, package management through integration with the Home Assistant Community Store (HACS), and advanced automation management with support for complex triggers, conditions, and actions. The architecture emphasizes intelligent organization with area and floor-based device grouping, smart context awareness, historical data access, and robust error handling. Security is ensured through token-based authentication and rate limiting. The server is mobile-ready and works with any HTTP-capable client. It is built with TypeScript for type safety and includes extensive test coverage. Installation can be done via basic setup or recommended Docker setup, with environment variables for configuration. The project requires Node.js, NPM, Docker Compose, a running Home Assistant instance, and access tokens for integration. The server exposes a RESTful API and SSE endpoints for seamless integration with LLMs and other clients. Overall, this project facilitates advanced, natural language-driven smart home automation and monitoring by leveraging the Model Context Protocol and LLMs, making smart home management more intuitive and accessible.
https://github.com/tevonsb/homeassistant-mcp
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.