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
OpenMCP is an open-source project that provides a standard and registry for converting various web APIs into Model Context Protocol (MCP) servers. This enables efficient integration of these APIs with MCP clients, such as large language models (LLMs). The project serves two main purposes: first, it defines a standard for transforming web APIs into MCP servers; second, it maintains an open-source registry of these servers that adhere to the standard. Each OpenMCP server allows MCP clients to make requests to specific web APIs in a token-efficient manner, facilitating data retrieval and action execution across diverse domains. The registry collectively represents a wide range of services, empowering LLMs to interact with multiple APIs seamlessly. The project documentation includes detailed instructions on creating an OpenMCP server, adding these servers to MCP clients through remote or local hosting, and converting different types of web APIs (such as REST, gRPC, JSON-RPC, GraphQL, SOAP, and PostgREST) into OpenMCP servers. The project supports integration with various clients like Claude desktop and Cursor, providing CLI commands and configuration steps to enable server usage. OpenMCP aims to streamline the process of connecting LLMs and other MCP clients to external APIs, enhancing their capabilities by enabling them to fetch data and perform actions efficiently and effectively.
https://github.com/wegotdocs/open-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.