Skip to main content
Glama
Trainerize MCP Server

Trainerize MCP Server

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

Yes, ChatGPT, Claude and other AI agents can work in your Trainerize account. Cotlet.dev connects your signed-in Trainerize account to AI agents so you can manage clients, programs, check-ins and messages.

What you can ask

List my Trainerize clients who have not been active in the last 7 days and group them by trainer.

Show Alex Rivera's goals, current programs and body stats for the last 90 days.

Find check-ins submitted this week and summarize the answers that need a reply.

List my appointments for next Monday and send Sam Carter a message confirming the time.

Subscribe all clients tagged Challenge to the 6-week Shred master program starting Monday.

Related MCP server: GeniusFitness MCP

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

Or with Docker:

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

Tools: trainerize_guide, trainerize_status, trainerize_open, trainerize_read, trainerize_click, trainerize_type, trainerize_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 trainerize-mcp        # or run it once: uvx trainerize-mcp connect
trainerize-mcp connect

Or straight from this repo:

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

Questions from Trainerize users

Does Trainerize have an API?

Trainerize offers API and webhook documentation for some integrations, while Cotlet.dev provides a hosted connection to your signed-in Trainerize account for the client, program, check-in and messaging tools.

How do I connect Trainerize to ChatGPT?

Add Cotlet.dev in ChatGPT with the connector URL https://cotlet.dev/mcp/v1/connect, sign in to Trainerize once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words.

Can I use Claude with Trainerize?

Yes. Add https://cotlet.dev/mcp/v1/connect as a custom connector in Claude, or use the Cotlet MCP server from Claude Code, and Claude can work with your Trainerize account.

What can the Trainerize MCP server do?

Cotlet.dev provides 14 Trainerize tools for clients, body stats, check-ins, conversations, programs, appointments, messages, tags and client status in ChatGPT, Claude and other AI agents.

Find it on

Also works with


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

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

Available Tools

7 tools
trainerize_clickB

Click a numbered element on the current Trainerize page.

Inputs: element (required).

trainerize_closeA

Close the Trainerize browser session when the work is done, so credits stop running.

Inputs: no named parameters.

trainerize_guideA

How to work in Trainerize (manage clients, programs, check-ins and messages): its screens and the sign-in link. Call this first.

Inputs: task.

trainerize_openB

Open a Trainerize page in your signed-in Cloud Browser (default https://trainerize.com) to work with manage clients, programs, check-ins and messages.

Inputs: url.

trainerize_readA

Read the current Trainerize page: its text and numbered buttons, links and fields.

Inputs: element.

trainerize_statusA

Check that your Cotlet.dev account and Trainerize are ready: account, credits and Trainerize connection.

Inputs: no named parameters.

trainerize_typeA

Type text into a numbered field on the current Trainerize page.

Inputs: text (required), element (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 7 tools

    Disambiguation4/5

    Each tool maps to a distinct browser-automation action (open, read, click, type, close) plus two informational tools. The only mild overlap is between trainerize_guide and trainerize_status, since both are 'call early' prerequisites, which could leave an agent briefly unsure which to invoke first.

    Naming Consistency5/5

    All seven tools use a uniform trainerize_<verb> or trainerize_<noun> snake_case convention with short, unambiguous names. The pattern is fully predictable across the set.

    Tool Count5/5

    Seven tools is well-scoped for a browser-driving server: a core action loop (open/read/click/type/close) plus onboarding and credential checks. No tool appears redundant or padding the surface.

    Completeness4/5

    The session lifecycle is fully covered from setup through read/act to teardown. Minor gaps remain for common browser needs such as explicit navigation to an arbitrary URL, scrolling long pages, and selecting dropdown options, which agents may have to work around via click/type.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables ChatGPT to manage fitness routines, guided sessions, workout history, body weight tracking, and statistics through a remote authenticated MCP server with read and write tools.
      AGPL 3.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to access and manage fitness programs, exercise catalog, workout resources, activity metrics, journaled plan edits, and change tracking through authenticated tools.
      51 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI assistants to plan, build, and log calisthenics workouts in a user's own account, including searching exercises, managing custom workouts and plans, reading progress and coaching data, and logging completed sessions. Account mutations require explicit confirmation, and workouts can be displayed as interactive cards in the chat.
      MIT
    • 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