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
mnhlt/WebSearch-MCP
WebSearch-MCP is a Model Context Protocol server, distributed on npm and runnable through npx, that exposes a single web search capability over stdio transport. The server itself is thin: it receives a search request from the MCP client, forwards it to a separate WebSearch Crawler API and returns the structured results, so the assistant gets current information from the open web instead of relying on training data. Two environment variables control it, one for the crawler API base URL and one for the default maximum number of results returned when the caller does not specify a limit. The crawler service is the part that does the real work and is meant to be self-hosted. The README supplies a Docker Compose file that runs the published crawler image together with FlareSolverr, which exists to get past Cloudflare interstitials; a separate variant of the file is given for Apple Silicon machines where the crawler image must be pinned to linux/amd64 while FlareSolverr runs as linux/arm64. The crawler listens on a configurable port, has a health endpoint that reports whether FlareSolverr and Google are reachable, and accepts crawl requests carrying a query, a result count, a language and filters such as excluded domains and a result type. Because the crawler is a plain HTTP service it can be tested with curl independently of any MCP client. Integration instructions are given for Claude Desktop, Cursor and Cline, and the package can also be consumed as a library rather than as a standalone process. The project is written in JavaScript and TypeScript, ships troubleshooting notes split between crawler problems and MCP server problems, and is aimed at anyone who wants search grounding for an assistant on infrastructure they control rather than through a commercial search API.
https://github.com/mnhlt/WebSearch-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.