Skip to main content
Glama

Fitune API and MCP server for ChatGPT and Claude

Fitune publishes no public API documentation or MCP server, according to the Cotlet.dev page checked 16 November 2026. Cotlet.dev connects ChatGPT, Claude and other AI agents to your Fitune studio admin through a hosted MCP server with 32 workflow tools. Writes ask for your approval by default.

What you can ask

Book a client into a class.

Read a client's upcoming and past bookings.

Create a group class and its schedule.

Send a payment link for an unpaid invoice after my approval.

Read studio revenue, refunds and discounts.

Prepare staff payroll for my review.

Related MCP server: Exercise.com MCP Server

Connect in 2 minutes

Start at https://cotlet.dev/signup?app=fitune, sign in to Fitune in your Cotlet Cloud Browser, and create an API key in the console for editors or scripts. Export the key as COTLET_API_KEY.

ChatGPT

Settings → Apps & Connectors → Create, add connector URL https://cotlet.dev/mcp/v1/connect, then sign in with Cotlet.dev using OAuth.

Claude

Settings → Connectors → Add custom connector, enter 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 Fitune 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":{"fitune":{"command":"uvx","args":["fitune-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}

Or with Docker:

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

Tools: fitune_guide, fitune_status, fitune_open, fitune_read, fitune_click, fitune_type, fitune_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 fitune-mcp        # or run it once: uvx fitune-mcp connect
fitune-mcp connect

Or straight from this repo:

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

Questions from Fitune users

Does Fitune have a public API or MCP server?

The Cotlet.dev page, checked 16 November 2026, reports no public Fitune API documentation, MCP server or official ChatGPT or Claude connector.

What can I do with the hosted Fitune integration?

The live page describes 32 workflow tools covering clients, classes, bookings, memberships, invoices and studio payroll. The local server in this repository exposes seven browser helper tools and forwards calls to Cotlet.dev.

Is this an official Fitune integration?

No. Cotlet.dev is independent and is not affiliated with, endorsed by or sponsored by Fitune.

Source

Fitune integration and all 32 hosted workflow tools


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

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

Available Tools

7 tools
fitune_clickB

Click a numbered element on the current Fitune page.

Inputs: element (required).

fitune_closeA

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

Inputs: no named parameters.

fitune_guideA

How to work in Fitune (studio classes, bookings, memberships, invoices and payroll): its screens and the sign-in link. Call this first.

Inputs: task.

fitune_openA

Open a Fitune page in your signed-in Cloud Browser (default https://admin.fitune.io) to work with studio classes, bookings, memberships, invoices and payroll.

Inputs: url.

fitune_readB

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

Inputs: element.

fitune_statusB

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

Inputs: no named parameters.

fitune_typeB

Type text into a numbered field on the current Fitune 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

    A3.5/5.0

    Scored across 7 tools

    Disambiguation4/5

    Each tool maps to a distinct step in a browser automation lifecycle (guide, status, open, read, click, type, close), so selection is largely unambiguous. The only mild overlap is between fitune_guide and fitune_status, both framed as pre-flight checks, with competing 'call this first' guidance.

    Naming Consistency4/5

    All seven tools share a uniform snake_case 'fitune_' prefix and short, readable names. Minor deviation: open/read/click/type/close are verbs while guide and status are nouns, so the pattern isn't a strict verb_noun convention.

    Tool Count5/5

    Seven tools is well-scoped for driving a single web app: one setup, one session open/close pair, one read, and two interaction primitives. Nothing appears redundant or padded.

    Completeness3/5

    The core loop (open → read → click/type → close) is covered, but there is no scroll, no key/submit primitive, and no select/dropdown handling, which will bite on long or form-heavy studio admin pages. Agents can partially work around this by re-reading or re-opening with an explicit URL.

    Related MCP Connectors

    • 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
    • Zen Planner MCP server for ChatGPT, Claude and any AI agent: list members, book class, record attendance, enroll in membership and list failed payments in your own Zen Planner account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Zen Planner yourself; Cotlet does not store your password and you need no Zen Planner API key. About the official Zen Planner API: Yes, but only for partners: Zen Planner has an API on the Daxko Partners portal, and its docs say "Contact your Daxko sales representative to request access" (checked 11 Oct 2026). Studios cannot create a key themselves in Zen Planner Studio. Setup and FAQ: https://cotlet.dev/integrations/zen-planner-api-mcp-server

    • Virtuagym MCP server for ChatGPT, Claude and any AI agent: book member into class, list classes, list members, add lead and add member note in your own Virtuagym account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Virtuagym yourself; Cotlet does not store your password and you need no Virtuagym API key. About the official Virtuagym API: Virtuagym has an API, but its docs and keys come only by email: "please reach out to api@virtuagym.com and provide us with your Github username" (checked 9 Nov 2026). It has no Zapier app and no official MCP server. Setup and FAQ: https://cotlet.dev/integrations/virtuagym-api-mcp-server

    • Glofox MCP server for ChatGPT, Claude and any AI agent: book member into class, list classes, list members, add lead and check in member in your own Glofox account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Glofox yourself; Cotlet does not store your password and you need no Glofox API key. About the official Glofox API: Glofox has a REST API for members, memberships, classes, bookings and payments, but the key and token come only on request to ABC Fitness, and its Zapier app needs the Elite plan (checked 8 Nov 2026). It has no official MCP server. Setup and FAQ: https://cotlet.dev/integrations/glofox-api-mcp-server

      https://cotlet.dev/mcp/v1/glofox

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables ChatGPT, Claude and other AI agents to work inside a signed-in Eversports Studio Manager account through Cotlet — viewing studio activities and sign-in lists, signing participants in, pausing or resuming memberships, and emailing invoices, with user approval before any change is saved. It runs as a hosted connector or a local stdio server that forwards tool calls to Cotlet.
      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
      Enables ChatGPT, Claude, and other AI agents to work with attendance, leads, memberships, and member messages in a signed-in Gymdesk account, including check-ins and approved messaging.
      Elastic 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Connects an AI agent to your own signed-in PushPress Core staff account so it can list classes and rosters, check members in, book or remove reservations, look up members and plans, report no-shows and late cancels, and message or cancel classes with approval for sensitive steps. It runs as a local stdio server that forwards calls to the hosted Cotlet.dev endpoint.
      Elastic 2.0