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
JamsusMaximus/trainingpeaks-mcp
TrainingPeaks MCP Server connects the TrainingPeaks endurance-training platform to MCP clients. Read tools cover completed workouts and the platform's training-load metrics — chronic training load, acute training load and training stress balance — plus power records, so an assistant can answer questions about fitness trends and progression such as comparing FTP over successive seasons. Write tools go further than reporting: the server can construct structured interval workouts, for example a threshold session with specified interval length, repetitions, warm-up and cool-down, and place them on a specific date and time in the training calendar. The authentication approach is the project's main practical claim. TrainingPeaks' official API is approval-gated and unavailable to ordinary users, so the server instead authenticates with a session cookie the user extracts once. That cookie is kept in the operating system keyring rather than a configuration file, and the README states it is sent only to TrainingPeaks. This makes the server usable with any account, at the cost of depending on an unofficial access path that a platform change could break. It is written in Python and documented for Claude Desktop, Claude Code and Cowork. The audience is cyclists and runners who plan in TrainingPeaks and want to build and review sessions conversationally.
https://github.com/JamsusMaximus/trainingpeaks-mcp
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.