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
DuarteSantos8/openGym
openGym is a self-hosted workout and gym-tracking application distributed as a Docker Compose stack, with native-feeling apps for iPhone, Android and the web (installable PWA, passkey sign-in, offline support, multi-device sync). It keeps all data, including routines, workout logs, body-weight history and progress photos, on the user's own server instead of a vendor's cloud, with no subscription, ads or telemetry. Planning features include a library of over 5,600 exercises with animated demos and muscle-map browsing, four starter programs (push/pull/legs, upper/lower, full body, 5x5), supersets, drop sets, rest-pause and timed or cardio exercises, and either a weekday schedule or a day-agnostic A/B/C rotation. During training it pre-fills weights from the last session, runs rest timers, detects personal records, and computes plate math for barbell, EZ bar, trap bar and Smith-machine setups. Progress tracking covers per-exercise or per-routine progression rules (linear, Greyskull, double/triple progression), an estimated one-rep-max curve, structural-balance ratios, and a year-long training heatmap. Two optional AI-adjacent features sit on top of the core tracker and are off by default: an AI coach that reads a user's training history and answers questions using a provider key the user supplies (Anthropic, OpenAI, Gemini or an OpenAI-compatible endpoint, including local Ollama), and a local MCP server that exposes the same training history to an MCP client such as Claude Desktop, letting the assistant answer questions about past workouts or log a new one described in natural language. Both are opt-in, run locally, and are excluded from the default Docker build; the project's CI test suite covers the frontend, API and MCP components separately. openGym is AGPL-3.0 licensed and supported through voluntary donations rather than a paid tier.
https://github.com/DuarteSantos8/openGym
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.
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.