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
mcp-server-openai is a small Python Model Context Protocol server whose purpose is to let one assistant query another: it exposes OpenAI models to Claude over MCP, so a question can be forwarded to an OpenAI model and its answer returned inside the Claude conversation. The repository is deliberately minimal and the README documents little beyond setup, testing and licence. Configuration happens entirely on the client side. An mcpServers entry in claude_desktop_config.json runs python with the -m flag against src.mcp_server_openai.server, and passes two environment variables: PYTHONPATH, set to the absolute path of the cloned repository so the module resolves, and OPENAI_API_KEY, holding the key the server authenticates to OpenAI with. The Windows-style path in the example suggests the author developed against Claude Desktop on Windows, though nothing in the setup is platform-specific. Development is the usual clone and editable install: git clone, then pip install -e in the project root. Testing runs pytest against test_openai.py from the project root with the -s flag so output is not captured, and the README shows the expected console output, a live call to the OpenAI API followed by a model reply, which means the test suite exercises the real API rather than a mock and therefore consumes credits. The project is MIT licensed and includes a preview image of the server in use. Because the README does not enumerate tool names, parameters or supported model identifiers, the exact surface has to be read from the source. It is aimed at people who want a second model available as a tool inside Claude, for cross-checking answers or for reaching capabilities one provider has and the other does not, and at anyone wanting a compact example of a Python MCP server.
https://github.com/pierrebrunelle/mcp-server-openai
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.