Workout MCP Server
@ipdelete
About Workout MCP Server
MCP Server for workout info
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"workout_mcp_server": {
"command": "python",
"args": [
"-m",
"workout_mcp_server"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Workout MCP Server?
A Model Context Protocol (MCP) server that provides cycling workout analytics tools, enabling LLMs to analyze fitness data, calculate training metrics, and provide insights into athletic performance.
How to use Workout MCP Server?
Install via uvx workout_mcp_server (recommended) or pip install workout_mcp_server and run with python -m workout_mcp_server. Configure with Claude Desktop or VS Code MCP Client by adding the server configuration to the appropriate JSON file. Use the provided tools to retrieve workouts and compute fitness, fatigue, and form scores.
Key features of Workout MCP Server
- Retrieves workout history (last 50 or last 7 workouts)
- Looks up specific workouts by unique ID
- Computes CTL (Fitness) via 42-day weighted average of TSS
- Computes ATL (Fatigue) via 7-day weighted average of TSS
- Computes TSB (Form) as difference between fitness and fatigue
- Provides structured workout data including TSS, power, distance, and type
Use cases of Workout MCP Server
- Analyze training load and recovery status for cyclists
- Provide insights on workout history and performance trends
- Assist athletes in planning training cycles based on metrics
- Enable AI assistants to answer fitness-related queries
FAQ from Workout MCP Server
What fitness metrics does the server compute?
It computes CTL (Fitness), ATL (Fatigue), and TSB (Form) using exponentially weighted moving averages of Training Stress Score (TSS).
How do I install and run the server?
Use uvx workout_mcp_server with uv (no installation needed) or run pip install workout_mcp_server then python -m workout_mcp_server.
What data does a workout contain?
Each workout includes id, date, duration_minutes, distance_km, avg_power_watts, tss, and workout_type. The dataset is built-in (50 workouts).
How do I configure it with Claude Desktop?
Add the appropriate JSON block to your claude_desktop_config.json under mcpServers, using either uvx or python -m depending on your installation method.
Are there any dependencies or runtime requirements?
Python is required; uv is optional but recommended. No external data source or authentication is needed—workouts come from a built-in dataset.
Frequently asked questions
What fitness metrics does the server compute?
It computes CTL (Fitness), ATL (Fatigue), and TSB (Form) using exponentially weighted moving averages of Training Stress Score (TSS).
How do I install and run the server?
Use `uvx workout_mcp_server` with uv (no installation needed) or run `pip install workout_mcp_server` then `python -m workout_mcp_server`.
What data does a workout contain?
Each workout includes id, date, duration_minutes, distance_km, avg_power_watts, tss, and workout_type. The dataset is built-in (50 workouts).
How do I configure it with Claude Desktop?
Add the appropriate JSON block to your `claude_desktop_config.json` under `mcpServers`, using either `uvx` or `python -m` depending on your installation method.
Are there any dependencies or runtime requirements?
Python is required; uv is optional but recommended. No external data source or authentication is needed—workouts come from a built-in dataset.
Basic information
More Other MCP servers
Website
FunnyWolfAdversary simulation and Red teaming platform with AI
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
MaxKB
1Panel-dev🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
Nginx UI
0xJackyYet another WebUI for Nginx
Comments