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
r-huijts/strava-mcp
The project "r-huijts/strava-mcp" is a Model Context Protocol (MCP) server implemented in TypeScript that serves as a bridge to the Strava API. It enables Large Language Models (LLMs) to access and interact with Strava data through the MCP standard by exposing Strava functionalities as AI-friendly tools. The server provides comprehensive access to Strava data including recent activities, user profiles, detailed activity streams such as power, heart rate, and cadence, as well as segments and segment efforts. Users can explore, view, star, and manage segments, and also list and view details of saved routes. Additionally, the server supports exporting routes in GPX or TCX formats to the local filesystem. The project is designed to facilitate natural language interaction with Strava data, allowing users to query their activities, stats, clubs, segments, and routes using conversational prompts. Examples include requests for recent rides, heart rate data, elevation profiles, running stats, segment details, and route exports. The server returns AI-friendly JSON responses, making it suitable for integration with AI assistants like Claude. An advanced use case demonstrated in the project is the creation of a professional cycling coach analysis of recent Strava activities, combining quantitative data with textual interpretation and interactive visualizations. This highlights the server's capability to support complex, data-driven AI applications. The setup process involves cloning the repository, installing dependencies, building the project, configuring the server in Claude's configuration, completing the Strava authentication flow, and restarting Claude. The server handles token refreshing automatically to maintain continuous access to the Strava API. Overall, this project provides a powerful and flexible MCP server that bridges Strava's rich fitness data with AI models, enabling innovative and interactive fitness data analysis and management through natural language interfaces.
https://github.com/r-huijts/strava-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.