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
rust-mcp-stack/rust-mcp-filesystem
Rust MCP Filesystem is an asynchronous Model Context Protocol server for filesystem operations, written as a pure Rust rewrite of the JavaScript @modelcontextprotocol/server-filesystem. It keeps the same role, giving an MCP client controlled access to files and directories, but aims at higher throughput and a smaller footprint by using async I/O and compiling to a single standalone binary with no Node.js or Python runtime required. Safety is handled by defaults: the server starts read-only and grants write access only when explicitly configured, and MCP roots support, which lets a client change the list of allowed directories at run time, is disabled unless turned on. Search goes beyond simple name matching and accepts full glob syntax, so patterns such as *.rs, src/**/*.txt or logs/error-???.log can select file types, recurse through directories or match structured filenames. Beyond reading and writing it provides archive tools that create ZIP files from files or directories and extract existing ZIP archives. Individual tools can be disabled to shrink the exposed surface and reduce the number of tool definitions sent to the model, which saves context tokens. Distribution is broad: shell and PowerShell installer scripts, a Homebrew tap, cargo install, an npm package that wraps the same binary, prebuilt release binaries, and an image on the Docker Hub MCP Registry. Configuration and the full tool list live in a separate documentation site rather than the README. The server is built on the rust-mcp-sdk and rust-mcp-schema crates from the same organisation, which the authors also present as a starting point for writing other MCP servers in Rust. It is MIT licensed and suits users who want file exploration, automation or system integration from an assistant with predictable resource use.
https://github.com/rust-mcp-stack/rust-mcp-filesystem
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.