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.
Awesome MCP › Other MCP Servers
microsoft/markitdown
MarkItDown is a Python-based utility designed to convert a wide range of file formats and office documents into Markdown format, facilitating integration with Large Language Model (LLM) applications through an MCP (Model Context Protocol) server. The tool supports numerous file types including PDF, PowerPoint, Word, Excel, images (with OCR and EXIF metadata), audio (with speech transcription and EXIF metadata), HTML, text-based formats like CSV, JSON, XML, ZIP archives, YouTube URLs, and EPUBs. MarkItDown emphasizes preserving important document structures such as headings, lists, tables, and links in the Markdown output, making it suitable for text analysis and LLM consumption rather than high-fidelity document rendering for human readers. Markdown is chosen as the output format because it is close to plain text with minimal markup, yet it effectively represents document structure. This format is natively understood by mainstream LLMs like OpenAI's GPT-4o, which often generate Markdown in their responses, indicating their training on Markdown-formatted text. The tool supports optional dependencies for handling specific file types, allowing users to install only the necessary components. It also supports third-party plugins to extend functionality. MarkItDown offers a command-line interface, Python API, and Docker support, making it versatile for different user preferences and environments. It integrates with Microsoft Azure Document Intelligence for enhanced document processing and supports LLM-based image descriptions by connecting to LLM clients like OpenAI. The project encourages community contributions and follows Microsoft's open-source code of conduct. Overall, MarkItDown is a powerful tool for converting diverse document formats into a structured, LLM-friendly Markdown format, with MCP server integration enabling advanced text analysis workflows.
https://github.com/microsoft/markitdown
Also in Other MCP Servers
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.
wanshuiyin/Auto-claude-code-research-in-sleep
ARIS (Auto-Research-In-Sleep) is a lightweight, framework-agnostic methodology and set of skills for autonomous ML research, enabling cross-model review loops, idea discovery, and experiment automa...