Skip to main content
Glama

Gymvio MCP server for ChatGPT and Claude

Gymvio publishes no public API or official MCP server, according to the Cotlet.dev page checked 17 November 2026. Cotlet.dev connects ChatGPT, Claude and other AI agents to your own signed-in Gymvio coach account through 23 hosted tools. The 5 read tools run directly; the 18 write tools ask for confirmation by default.

What you can ask

Review weekly check-ins and draft replies.

Spot failed sets in logged workouts.

Assign a training block to many clients after my approval.

Build a diet plan with macros calculated.

Draft a nudge for clients who are off plan.

Related MCP server: WeStrive MCP Server

Connect in 2 minutes

Sign up at https://cotlet.dev/signup?app=gymvio, enable Gymvio and sign in at https://gymvio.com/login in your Cloud Browser. Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.

ChatGPT

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

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 the local MCP bridge

Python 3.10+, with no dependencies. Clone this repository, set your Cotlet.dev API key, then run:

export COTLET_API_KEY="your-key"
python3 gymvio_agent.py serve

This local stdio bridge lists seven browser helper tools: gymvio_guide, gymvio_status, gymvio_open, gymvio_read, gymvio_click, gymvio_type and gymvio_close. It forwards calls to the hosted Cotlet.dev MCP server. The 23 task tools described on the integration page are available through the hosted connection.

Without a key, the local bridge can list its helpers; calls return setup instructions.

python3 gymvio_agent.py connect
python3 gymvio_agent.py guide
python3 gymvio_agent.py status

Questions from Gymvio users

Does Gymvio have an API or official MCP server?

The Cotlet.dev page checked 17 November 2026 found no public Gymvio API documentation, official MCP server or official ChatGPT or Claude connector.

How do I connect Gymvio to ChatGPT or Claude?

Sign up at https://cotlet.dev/signup?app=gymvio, enable Gymvio and sign in at https://gymvio.com/login in your Cloud Browser. Add https://cotlet.dev/mcp/v1/connect as the connector URL and sign in to Cotlet.dev.

Do my clients need anything for this?

No. Clients keep using Gymvio on their phones; Cotlet.dev works in your coach account.

Is this an official Gymvio integration?

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

Integration details

Gymvio tools and setup on Cotlet.dev


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

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

Available Tools

7 tools
gymvio_clickB

Click a numbered element on the current Gymvio page.

Inputs: element (required).

gymvio_closeA

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

Inputs: no named parameters.

gymvio_guideA

How to work in Gymvio (review client check-ins and workout logs, prepare training and nutrition plans and draft messages): its screens and the sign-in link. Call this first.

Inputs: task.

gymvio_openA

Open a Gymvio page in your signed-in Cloud Browser (default https://gymvio.com/login) to work with review client check-ins and workout logs, prepare training and nutrition plans and draft messages.

Inputs: url.

gymvio_readA

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

Inputs: element.

gymvio_statusA

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

Inputs: no named parameters.

gymvio_typeC

Type text into a numbered field on the current Gymvio 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 workflow (guide, readiness check, open, read, click, type, close), so an agent can sequence them without guessing. The only mild overlap is between gymvio_guide and gymvio_status, both of which are pre-flight informational tools, but their descriptions clearly separate site instructions from account/credit/connection checks.

    Naming Consistency4/5

    All seven tools share the gymvio_ prefix and a single lowercase suffix, giving a highly predictable namespace. The suffixes mix noun-style (guide, status) with verb-style (open, read, click, type, close) entries, a minor deviation that does not impede recognition.

    Tool Count5/5

    Seven tools is well-scoped for a site-specific browser automation surface, with each tool earning its place as a primitive or onboarding step. Nothing is redundant and nothing feels arbitrarily withheld.

    Completeness4/5

    The core loop is covered: onboard, verify access, open a page, read its elements, interact via click and type, and close the session to stop credit usage. Gaps remain around scrolling long pages, explicit submit/keypress actions, and select-style widgets, which agents would have to work around with repeated read/click calls.

    Related MCP Connectors

    • 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

    • TrueCoach MCP server for ChatGPT, Claude and any AI agent: list clients, create workout, assign program, read workout results and message client in your own TrueCoach account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to TrueCoach yourself; Cotlet does not store your password and you need no TrueCoach API key. About the official TrueCoach API: TrueCoach has no public API and no developer docs (checked 11 Oct 2026). The only programmatic access is its Zapier app, which its help center lists for the Pro plan or higher: 4 triggers and 1 action, "Add a Client to TrueCoach". Setup and FAQ: https://cotlet.dev/integrations/truecoach-api-mcp-server

    • 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

    Related MCP Servers

    • A
      license
      A
      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.
      7
      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
    • A
      license
      Not graded
      quality
      C
      maintenance
      Connects Fitsly coach accounts to ChatGPT, Claude, and AI agents through Cotlet.dev, exposing hosted tools for clients, training, nutrition, habits, messages, and packages with approval-gated write actions.
      Elastic 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to work within a coach's Hevy Coach account through Cotlet.dev, covering client activity, programs, exercises, progress pictures, chat, teams, and leads. Write actions require approval by default.
      Elastic 2.0