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
leehanchung/bing-search-mcp
Bing Search MCP Server connects MCP-compatible assistants to the Microsoft Bing Search API so a model can look things up on the web during a conversation. Three tools are documented. The web search tool runs a general query and accepts a result count, an offset for paging through results, and a market code that defaults to United States English. The news search tool retrieves articles and current events with the same count and market parameters plus a freshness parameter, defaulting to the last day, that limits how recent the results must be. The image search tool returns visual results for a query with count and market parameters. Beyond the tools themselves the README lists rate limiting to avoid abusing the upstream API quota, and error handling across the three search paths. Requirements are Python 3.10 or later, a Bing Search API key, and an MCP-compatible client; Claude Desktop and Cursor are named as examples. Installation is from a clone of the repository using uv to create a virtual environment and install the package in editable mode, after which the server runs through uvx. Two environment variables configure it: the API key, which is required, and an optional endpoint URL that defaults to the public Bing endpoint, with the README giving both shell and Windows command prompt forms. Registration with Claude Desktop is shown as a JSON block naming the command, the path to the checkout, and the API key passed in the environment, with the configuration file location given for macOS and Windows. The README also links Smithery for automated installation and walks through obtaining a key by creating a Bing Search resource in the Azure portal. Released under the MIT licence.
https://github.com/leehanchung/bing-search-mcp
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.