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
ac3xx/mcp-servers-kagi
kagi-server is a small TypeScript MCP server that integrates the Kagi Search API, presented by its author as a demonstration of core Model Context Protocol concepts as much as a finished product. One tool is implemented: kagi_search takes a query string and an optional result limit and returns results from the Kagi API, which at the time of writing was in private beta and therefore requires an account with access. Three further tools are described in the README as planned but not yet built, and the documentation is unusually direct about this, repeating that they cannot be used. Those planned tools are kagi_summarize for summarising web pages or arbitrary text, kagi_fastgpt for quick answers through the Kagi FastGPT endpoint, and kagi_enrich for pulling enriched news results on a topic; the same three appear again in the roadmap alongside better error handling and input validation, more usage examples and publication of the package to npm. Configuration is a single environment variable holding the Kagi API key, read from a .env file that the README reminds the user to keep out of version control. Development follows the usual Node pattern of install, build and a watch mode for automatic rebuilds. Two installation routes are given: an automatic one through Smithery targeting Claude Desktop, and a manual one where the built entry point is registered in the Claude Desktop configuration file for the current platform with the API key passed through the environment. For debugging the README recommends the official MCP Inspector, wired up as a package script, because a stdio server is otherwise awkward to observe. Contributions are invited, particularly for the unimplemented tools, and the project is MIT licensed. It suits Kagi subscribers who want search results available inside an assistant.
https://github.com/ac3xx/mcp-servers-kagi
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.