Skip to main content
Glama

Fitsly MCP server

Connect Fitsly to ChatGPT, Claude and any AI agent through Cotlet.dev. Work in your own coach account with 10 hosted tools for clients, training, nutrition, habits, messages and packages. Write actions ask for approval by default.

What you can ask

Rank my clients by program progress before Monday check-ins.

Read the food log for Jamie Example today.

Prepare a hydration habit for my client group and show it for approval before assigning it.

Related MCP server: Exercise.com MCP Server

Connect in 2 minutes

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

ChatGPT

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

Claude

Settings → Connectors → Add custom connector, with URL https://cotlet.dev/mcp/v1/connect, then sign in with Cotlet.dev.

Claude Code

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

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 Fitsly 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.

Run the included Python module with Python 3.10 or later:

python3 fitsly_agent.py serve

Or with Docker:

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

Tools: fitsly_guide, fitsly_status, fitsly_open, fitsly_read, fitsly_click, fitsly_type, fitsly_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+, with no third-party runtime dependencies. Clone this repository and run:

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

Questions from Fitsly users

Which Fitsly account should I connect?

Sign in to your own coach account at app.fitsly.com/login in the Cotlet Cloud Browser.

Which actions ask for approval?

The eight write tools ask for approval by default. The two read tools cover client overviews and food logs.

Is Cotlet affiliated with Fitsly?

No. Cotlet.dev is independent and not affiliated with Fitsly.

Learn more


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

Request access: https://cotlet.dev/signup?app=fitsly&utm_source=github&utm_medium=readme&utm_campaign=fitsly

Workflows on the hosted integration

The live integration page documents these 10 operations:

  • manage_clients

  • get_client_overview

  • build_workout

  • manage_phased_program

  • manage_meal_plans

  • set_macro_targets

  • get_food_log

  • manage_habits

  • send_message

  • manage_packages

The local stdio adapter exposes seven browser helpers listed above. These helpers forward to Cotlet.dev; the workflow operations are documented on the hosted integration page.

Tool Schema Changelog

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

Loading tool schema changelog…

    Related MCP Connectors

    • FitSW MCP server for ChatGPT, Claude and any AI agent: add client, assign program, create workout, check compliance and list clients in your own FitSW account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to FitSW yourself; Cotlet does not store your password and you need no FitSW API key. About the official FitSW API: FitSW publishes no public API, webhooks or Zapier app (checked 9 Nov 2026). It has no official MCP server. Setup and FAQ: https://cotlet.dev/integrations/fitsw-api-mcp-server

      https://cotlet.dev/mcp/v1/fitsw
    • FitBudd MCP server for ChatGPT, Claude and any AI agent: add client, schedule workout, review check-ins, add client note and list clients in your own FitBudd account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to FitBudd yourself; Cotlet does not store your password and you need no FitBudd API key. About the official FitBudd API: FitBudd publishes no public API; its developer docs return "gone". Its only connection is a Zapier app with triggers only, on the Super Pro plan and higher (checked 9 Nov 2026). Setup and FAQ: https://cotlet.dev/integrations/fitbudd-api-mcp-server

      https://cotlet.dev/mcp/v1/fitbudd
    • Everfit MCP server for ChatGPT, Claude and any AI agent: list clients, get client overview, assign program, read body metrics and message client in your own Everfit account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Everfit yourself; Cotlet does not store your password and you need no Everfit API key. About the official Everfit API: Everfit has an API, but only for Enterprise customers, who ask the Enterprise team by email for a token (checked 11 Oct 2026). It manages clients, programs, Autoflows, collections, groups and forums, and sends two webhooks; its guide lists no endpoints for messages, body metrics, tasks or workout results. Setup and FAQ: https://cotlet.dev/integrations/everfit-api-mcp-server

      https://cotlet.dev/mcp/v1/everfit
    • Trainerize MCP server for ChatGPT, Claude and any AI agent: list clients, assign program, message client, log body stats and schedule appointment in your own Trainerize account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Trainerize yourself; Cotlet does not store your password and you need no Trainerize API key. About the official Trainerize API: Trainerize has an API, but only on Studio and Enterprise plans or with the paid FitMetrics add-on (checked 10 Oct 2026). Grow and Pro trainers get Zapier, not the API, and there is no public API reference. Setup and FAQ: https://cotlet.dev/integrations/trainerize-api-mcp-server

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Connects AestheticsPro accounts to ChatGPT, Claude, and other AI agents through Cotlet, enabling appointment scheduling, client contact access, lead creation, and staff assignment with user approval.
      7
      Elastic 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents like ChatGPT, Claude, and Cursor to work inside a user's own signed-in Exercise.com account, viewing schedules, booking sessions, messaging clients, and handling invoices with approval steps. It runs as a hosted connector or a local stdio server that forwards tool calls to the hosted backend using a Cotlet API key.
      Elastic 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Connects a signed-in WeStrive coaching account to ChatGPT, Claude, Cursor, and other AI agents so users can read client lists, review progress, assign training programs, schedule check-ins and reminders, set nutrition goals, and send coaching messages. It also ships a local stdio adapter that forwards tool calls to the hosted Cotlet.dev service.
      Elastic 2.0