IGPSPORT-MCP

Created By

dengxuhuia month ago

Local MCP server exposing iGPSport cycling data to LLM clients. Computes training metrics (NP/IF/TSS/CTL/ATL/TSB) server-side, supports 17 tools including activity analysis, segment leaderboards, workout generation, and threshold estimation.

# cycling

# fitness

Overview Content Comments

Content

iGPSport MCP is a local stdio MCP server that bridges iGPSport cycling data into LLM clients (Claude Desktop, Claude Code, etc.).

Key features:

17 MCP tools: activity list/detail/streams/laps, segment explorer (CN only), athlete stats, training load (CTL/ATL/TSB), threshold estimation, workout generation
Server-side derived metrics: Normalized Power, Intensity Factor, TSS, hrTSS, Coggan 7-zone power distribution, Friel HR zones
Dual-region: CN (prod.zh.igpsport.com) and INTL (app.igpsport.com)
Local-first: FIT files cached locally; zero server dependency beyond initial API fetch
Transport: stdio (uvx igpsport-mcp)

Install: uvx igpsport-mcp GitHub: https://github.com/dengxuhui/igpsport-mcp PyPI: https://pypi.org/project/igpsport-mcp/

Recommend Clients

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

DeepChatYour AI Partner on Desktop

Cline – #1 on OpenRouterAutonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

Roo Code (prev. Roo Cline)Roo Code (prev. Roo Cline) gives you a whole dev team of AI agents in your code editor.

Refact.aiOpen-source AI Agent for VS Code and JetBrains that autonomously solves coding tasks end-to-end.

chatmcpChatMCP is an AI chat client implementing the Model Context Protocol (MCP).

ChatWiseThe second fastest AI chatbot™

y-cli 🚀A Tiny Terminal Chat App for AI Models with MCP Client Support

WindsurfThe new purpose-built IDE to harness magic

Continue⏩ Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks