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
rohitg00/ai-engineering-from-scratch
This project, "AI Engineering from Scratch," offers a profound, hands-on curriculum for mastering AI development. It is designed to equip individuals with practical skills by having them build AI systems, including agents and Model Context Protocol (MCP) servers, from fundamental mathematical principles to advanced autonomous systems. The curriculum spans 20 phases and 503 lessons, accumulating to approximately 320 hours of work, utilizing Python, TypeScript, Rust, and Julia. Unlike traditional fragmented learning approaches, this course provides a cohesive, end-to-end learning path. It emphasizes understanding the underlying mechanics of AI rather than merely using APIs. Learners will implement algorithms such as backpropagation, tokenizers, and attention mechanisms from scratch before engaging with high-level frameworks like PyTorch, ensuring a deep comprehension of their internal workings. Each lesson follows a structured "Build It / Use It" approach, where concepts are derived mathematically, coded, tested, and a functional artifact (like a prompt, skill, agent, or MCP server) is produced. The project caters to those who can code and are committed to understanding AI's actual operation. It includes built-in agent skills for platforms like Claude and Cursor, enabling personalized learning paths and progress checks within the curriculum. With its focus on generative AI, large language models (LLMs), agent engineering, and the explicit mention of producing MCP servers, this resource is highly relevant for individuals and organizations looking to deeply engage with and contribute to the MCP ecosystem.
https://github.com/rohitg00/ai-engineering-from-scratch
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.
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...
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.
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.
DuarteSantos8/openGym
Self-hosted gym and workout tracker (Docker, PWA, passkey sync across devices) that also ships an optional local MCP server so an assistant like Claude Desktop can answer questions about training history or log a workout described in natural language.