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
dinoki-ai/osaurus
Osaurus is a native macOS LLM (Large Language Model) server designed specifically for Apple Silicon, providing a unified API to run both local and cloud-based language models. It supports the Model Context Protocol (MCP), enabling seamless integration with MCP clients such as Cursor and Claude Desktop. The project offers a comprehensive solution for running and managing language models locally using the MLX runtime optimized for Apple Silicon, as well as connecting to remote providers like OpenAI, OpenRouter, Ollama, and LM Studio through OpenAI-compatible APIs. Osaurus acts as an MCP server, exposing tools to AI agents and allowing aggregation of tools from external MCP servers. It features a plugin system that extends its capabilities with community and custom tools, including browser automation, file system operations, git commands, web search, and more. The server includes developer tools such as request insights, an API explorer, and live endpoint testing to facilitate debugging and development. Users can manage models easily with a built-in model manager that supports downloading models from Hugging Face. Osaurus also offers a menu bar chat overlay with a global hotkey for quick access. The project emphasizes security with features like secure API key storage in the macOS Keychain and connection health monitoring. It supports Apple Foundation Models on macOS 26+ (Tahoe) and provides a rich ecosystem for developers and users to interact with language models efficiently on macOS. Installation is straightforward via Homebrew or direct download, and the server runs on a default port with simple commands to start and manage the service. Overall, Osaurus is a powerful, versatile, and user-friendly LLM server tailored for macOS users who want to leverage both local and cloud AI models with MCP support and extensive tooling.
https://github.com/dinoki-ai/osaurus
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.