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
This server connects MCP clients to the Tavily search API so that a model can run web research through tool calls. The README carries a deprecation notice from the author: it was written in early March 2025 when MCP was new and no consistent search integration existed, and it is now deprecated in favour of the official Tavily MCP server, which stays in sync with the vendor current capabilities. Three tools are documented. The web search tool runs a general query with AI-powered content extraction and accepts a maximum result count capped at twenty, a search depth of basic or advanced, and lists of domains to include or exclude. The answer search tool runs the same kind of query but returns a direct generated answer with supporting evidence, defaulting to advanced depth. The news search tool retrieves recent articles with publication dates and adds a parameter for how many days back to look, defaulting to three. Each of the three also ships as a prompt template, so a client can offer them as ready-made prompts rather than only as raw tool calls. The server requires Python 3.11 or later and a Tavily API key, which can be supplied through a dotenv file in the project directory as well as other documented routes. Installation is available from PyPI with pip or uv, or from source with a virtual environment followed by uv sync and uv build; a development extra installs test dependencies. The README also documents Visual Studio Code integration, including one-click install links and a JSON block that registers the server under uvx with the API key collected as a masked prompt input, storable in user settings or a workspace file for sharing.
https://github.com/RamXX/mcp-tavily
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.