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
Website Downloader MCP Server wraps the wget utility in a single MCP tool, download_website, so a model can retrieve a whole site rather than one page at a time. The tool takes a required url and optional parameters: outputPath for the destination directory, defaulting to the current directory, and depth to bound recursive descent, where zero fetches only the given page, one follows direct links, and the default is unlimited. wget is invoked in mirroring mode, so the site's directory structure is preserved on disk and internal links are converted to relative paths that resolve against the local copy — the downloaded site is browsable offline rather than a pile of disconnected HTML. The server is a small JavaScript project whose only prerequisite is wget being installed and on PATH; the README gives installation commands for macOS via Homebrew, Debian and Red Hat family Linux, and Windows via Chocolatey or a prebuilt binary. Because it delegates entirely to wget, it inherits both wget's robustness and its limitations, notably no JavaScript rendering, so single-page applications will not mirror usefully. The audience is people who need an offline copy of documentation or a reference site for later analysis, where a model can then read the local files instead of making repeated network requests.
https://github.com/pskill9/website-downloader
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.