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
modelcontextprotocol/servers-archived
This repository holds the historical reference server implementations from the Model Context Protocol organization. It is archived and no longer maintained: it accepts no contributions, receives no bug fixes, and the README states plainly that no security guarantees are provided for the code it contains, so it should not be used in production. The active servers now live in the separate modelcontextprotocol/servers repository, which the README links to as the place to go for current implementations. The servers preserved here were written to demonstrate MCP features and the capabilities of the SDKs, and they cover a broad span of integrations: AWS Knowledge Base Retrieval, Brave Search, EverArt, Git, GitHub, GitLab, Google Drive, Google Maps, PostgreSQL, Puppeteer, Redis, Sentry, Slack and SQLite. Between them they illustrate the common server patterns of the early protocol, including version control access, web search, browser automation, database querying over both relational engines, cloud document access, mapping, error tracking and team chat. The code is released under the MIT license. Its value today is mainly as reading material and as a starting point for people studying how the first generation of MCP servers structured tools, resources and prompts, or tracing how a specific integration was originally implemented before it moved or was retired. Anyone looking for working, supported servers should follow the pointer in the README to the maintained repository rather than depend on anything here.
https://github.com/modelcontextprotocol/servers-archived
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.