Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@gymtracker log my latest workout: squat 3x5 at 315 lbs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Universal MCP server + Claude Code plugin for Gymtracker. Lets AI coding agents (Claude Code, Codex, Cursor, …) read and write your training data.
Your Gymtracker instance URL (GYMTRACKER_URL)
An API token from your Gymtracker /api/tokens page (GYMTRACKER_TOKEN)
Related MCP server: intervals.icu-mcp
Env | Read | Write | Delete |
(default) | ✅ | ✅ | ❌ |
| ✅ | ✅ | ✅ |
| ✅ | ❌ | ❌ |
READONLY overrides ALLOW_DELETE.
/plugin marketplace add https://gitlab.com/codin-public/gymtracker-plugin.git
/plugin install gym@gymtrackerYou'll be prompted for your URL and token. Adds /gym:log, /gym:summary, /gym:coach.
See examples/codex.md.
See examples/cursor.md and examples/generic-mcp.json.
Env is not inherited. stdio MCP servers don't see your shell env — put the vars in the
client's env block (or Cursor's ${env:...}).
npx on PATH. GUI clients launched from the Dock may not find npx (nvm/Homebrew).
Use an absolute path to npx/node in command if startup fails.
First run downloads. npx -y fetches the package once; bump Codex's
startup_timeout_sec if it times out.
npm install
npm test
npm run buildMIT
This server cannot be deployed
Adaptive running coach MCP server — training data, plans, and recovery for AI assistants.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
