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
automation-ai-labs/mcp-link
MCP Link is a project designed to automate the conversion of any OpenAPI V3 API into a fully compatible Model Context Protocol (MCP) Server. This enables seamless integration of existing RESTful APIs with AI Agent frameworks without requiring any modifications to the original APIs. The project addresses a significant gap in the AI Agent ecosystem where most MCP Servers are simple wrappers around Web APIs, often incomplete in functionality and manually created, which is time-consuming and error-prone. MCP Link solves these issues by providing an automated and standardized process to generate complete MCP Servers based on OpenAPI schemas. This ensures that all API endpoints and features are correctly mapped and accessible through the MCP interface. Key features of MCP Link include automatic conversion of OpenAPI specifications to MCP Servers, seamless integration with AI Agent calling standards, zero code modification of the original APIs, and adherence to the open MCP specification to guarantee compatibility with various AI Agent frameworks. The project also offers an online hosted version for quick conversion and testing of APIs without installation. The architecture of MCP Link supports filtering of API endpoints, authentication header configuration, and flexible usage scenarios. It supports various authentication methods such as API keys, bearer tokens, and API tokens, demonstrated through examples with popular APIs like Brave Search, DuckDuckGo, Figma, GitHub, Home Assistant, Notion, Slack, Stripe, TMDB, and YouTube. MCP Link is particularly useful for developers and organizations looking to integrate their existing APIs into AI-driven applications efficiently. Future development plans include support for OAuth authentication flows, enhanced resource handling, and improved MIME type support in API requests and responses. Overall, MCP Link streamlines the process of making APIs MCP-compatible, fostering a more connected and interoperable AI ecosystem.
https://github.com/automation-ai-labs/mcp-link
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.