Skip to main content
Glama
CoachingPortal MCP Server

CoachingPortal MCP Server

CoachingPortal MCP server for ChatGPT and Claude

Connect CoachingPortal to ChatGPT, Claude and other AI agents through Cotlet. Work with client check-ins, workout templates and training programs in your own signed-in account. Cotlet is independent and not affiliated with CoachingPortal.

What you can ask

List pending client check-ins for this week.

Create a private workout template from the exercises, sets and reps I provide. Ask me before saving.

Prepare feedback on the check-in I select. Ask for my approval before sending it.

Related MCP server: Garmin Connect 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 → add connector URL https://cotlet.dev/mcp/v1, then sign in with Cotlet.dev. No API key needed.

Claude

Add https://cotlet.dev/mcp/v1 as a custom connector in Claude and sign in with Cotlet.dev. Follow the steps in your Cotlet console.

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 CoachingPortal 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": {"coachingportal": {"command": "python3", "args": ["/absolute/path/to/coachingportal-mcp/coachingportal_agent.py", "serve"], "env": {"COTLET_API_KEY": "your-key"}}}}

Or with Docker:

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

Tools: coachingportal_guide, coachingportal_status, coachingportal_open, coachingportal_read, coachingportal_click, coachingportal_type, coachingportal_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. Run from this repo:

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

Questions from CoachingPortal users

How do I connect CoachingPortal to ChatGPT or Claude?

Sign up at cotlet.dev, log in to CoachingPortal once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your CoachingPortal account through Cotlet, in their phone apps too.

What can ChatGPT do in CoachingPortal?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in CoachingPortal: create workout template; assign workout program; review submitted check-ins. You ask in plain words, and anything that reaches other people waits for your OK first.

Can ChatGPT create program template in CoachingPortal?

ChatGPT saves a private CoachingPortal workout template from your workout days, exercises, sets, reps and loads. Saving the template does not assign it to a client.

Does CoachingPortal have an API?

CoachingPortal publishes no public API. Its FAQ, help center and pricing pages provide no developer documentation or self-serve API key. CoachGPT is built into CoachingPortal and is separate from an external ChatGPT or Claude connector.

Is Cotlet affiliated with CoachingPortal?

No. Cotlet is independent and not affiliated with CoachingPortal.

Find it on


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

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

Available Tools

7 tools
coachingportal_clickB

Click a numbered element on the current CoachingPortal page.

Inputs: element (required).

coachingportal_closeA

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

Inputs: no named parameters.

coachingportal_guideA

How to work in CoachingPortal (review client check-ins and training programs): its screens and the sign-in link. Call this first.

Inputs: task.

coachingportal_openB

Open a CoachingPortal page in your signed-in Cloud Browser (default https://app.coachingportal.io) to work with review client check-ins and training programs.

Inputs: url.

coachingportal_readA

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

Inputs: element.

coachingportal_statusA

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

Inputs: no named parameters.

coachingportal_typeA

Type text into a numbered field on the current CoachingPortal 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

    Disambiguation5/5

    Each tool has a clearly distinct role: guide and status are informational/setup, open/close manage the session lifecycle, and read/click/type are discrete page interactions. There is no meaningful overlap between tools.

    Naming Consistency5/5

    All tools use the same coachingportal_ prefix followed by a concise verb or noun, forming a predictable and readable pattern. The convention is consistent throughout.

    Tool Count5/5

    Seven tools are well-scoped for a browser-automation wrapper: setup guidance, status checking, session lifecycle, and the core read/click/type interactions. Each tool earns its place without unnecessary surface area.

    Completeness4/5

    The set covers the essential browser workflow—check readiness, open a page, inspect content, interact via click/type, and close the session. Minor gaps like explicit navigation, scrolling, waiting, or select handling exist, but agents can largely work around them with read and click.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers