Skip to main content
Glama

How to connect Everfit to ChatGPT, Claude and any AI agent

Yes, ChatGPT, Claude and other AI agents can work in your Everfit account. Cotlet.dev connects your own signed-in Everfit account to any AI agent, so you can check in on quiet clients, review progress and manage coaching activity in plain words.

What you can ask

Which clients have been quiet recently, and what are their last workout and check-in dates?

Show me weight and waist trends for Sam Rivera over the last 30 days.

Draft Inbox replies for clients who have not checked in this week, and show me the drafts first.

Assign the next program to the clients in my Monday coaching group after I review the list.

List active clients with incomplete workouts and summarize their progress for this week.

Related MCP server: Phorme Training

Connect in 2 minutes

Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.

Claude Code

claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"

ChatGPT

Settings → Apps → add connector URL https://cotlet.dev/mcp/v1, then sign in with Cotlet.dev. No API key needed.

Cursor

Copy .cursor/mcp.json from this repo into your project:

{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}

Run it locally (stdio)

This repo is a real MCP server. It speaks MCP over stdio, lists its Everfit tools without any key, and forwards every tool call to the hosted Cotlet.dev server. The hosted URL above stays the recommended way. Use this when your client only starts local servers.

{"mcpServers":{"everfit":{"command":"uvx","args":["everfit-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}

Or with Docker:

docker build -t everfit-mcp .
docker run -i --rm -e COTLET_API_KEY everfit-mcp

Tools: everfit_guide, everfit_status, everfit_open, everfit_read, everfit_click, everfit_type, everfit_close. Without COTLET_API_KEY a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".

Command line

Python 3.10+, nothing else to install. From PyPI:

pip install everfit-mcp        # or run it once: uvx everfit-mcp connect
everfit-mcp connect

Or straight from this repo:

export COTLET_API_KEY="your-key"
python3 everfit_agent.py connect   # ready config for Claude Code, Cursor, ChatGPT
python3 everfit_agent.py status    # is Everfit ready in your Cotlet.dev account
python3 everfit_agent.py guide     # Everfit screens and sign-in link
python3 everfit_agent.py read      # open Everfit, read the page, close the browser
python3 everfit_agent.py tools     # list Cotlet.dev tools
python3 everfit_agent.py serve     # start the stdio MCP server (same as no argument)

Questions from Everfit users

Does Everfit have an API for developers?

Everfit has an API for Enterprise customers on the 500+ client plan. Cotlet.dev works in your own Everfit account directly and exposes coaching clients, workouts, progress, Inbox and task workflows through MCP and REST.

How do I connect Everfit to ChatGPT?

Add Cotlet.dev as an app in ChatGPT using the MCP setup on this page, sign in to Everfit once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words. No Everfit API key is needed.

Is there a way to use Claude with Everfit?

Yes. Add the Cotlet.dev MCP URL as a custom connector in Claude or use the Claude Code command shown above. Claude then works in your own Everfit account.

Is there an Everfit MCP server?

Everfit does not publish a public MCP server. Cotlet.dev is a hosted MCP server that works in your Everfit account with ChatGPT, Claude, Cursor, Codex and other AI agents.

Find it on

Also works with


More: https://cotlet.dev/integrations/everfit-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=everfit

Start free: https://cotlet.dev/signup?app=everfit&utm_source=github&utm_medium=readme&utm_campaign=everfit

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI assistants to find coach-built training programs, coaching brains, races, gyms, classes and sports clinics, preview and build workouts with exercise demos, swap exercises, and plan around a sport or race. With OAuth it can also save workouts and programs, send coach notes to members, and read a member's logged history, planned sessions and lift progress.
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables read-only access to WHOOP recovery, sleep, HRV, strain, workout, and personal health analytics from AI assistants such as Claude, Codex, and GitHub Copilot. Users can ask natural-language questions about trends, baselines, sleep debt, training load, and race readiness without exporting their data.
      14 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to read training, sleep, recovery, nutrition, body composition, race and goal data, and with permission write workouts, daily targets, meal plans, logged meals and notes. Also supports checking for updates since the last look.
      MIT