Skip to main content
Glama
README.md
# PTminder MCP server

Connect PTminder to ChatGPT, Claude and any AI agent through Cotlet.dev. Reconcile sessions, manage bookings, assign workout plans and read client balances in your own signed-in trainer account. Write actions ask for approval by default.

## What you can ask

> List yesterday's sessions waiting to be reconciled.

> Find clients with outstanding balances and draft a reminder for my approval.

> Build a workout plan and show it to me before assigning it.

## 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

```bash
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:

```json
{
  "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 PTminder 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:

```bash
python3 ptminder_agent.py serve
```

Or with Docker:

```bash
docker build -t ptminder-mcp .
docker run -i --rm -e COTLET_API_KEY ptminder-mcp
```

Tools: `ptminder_guide`, `ptminder_status`, `ptminder_open`, `ptminder_read`, `ptminder_click`, `ptminder_type`, `ptminder_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:

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

## Questions from PTminder users

**Which PTminder login should I use?**

Sign in with your own trainer account in the Cotlet Cloud Browser, including the verification code if PTminder asks for one.

**Do payments and client messages ask for approval?**

Write actions, including charges and messages, ask for approval by default.

**Is Cotlet affiliated with PTminder?**

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

## Learn more

- [PTminder integration and hosted tools](https://cotlet.dev/integrations/ptminder-api-mcp-server)

---

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

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

## Workflows on the hosted integration

The live integration page documents these 32 operations:

- `find_clients`
- `get_client_summary`
- `list_client_sessions`
- `add_client`
- `remove_client`
- `record_client_note`
- `record_client_assessment`
- `book_session`
- `set_availability`
- `set_trainer_roster`
- `reconcile_session`
- `create_workout_plan`
- `record_workout`
- `create_nutrition_plan`
- `assign_package`
- `assign_membership`
- `adjust_service_credits`
- `change_membership_payments`
- `manage_recurring_card_payments`
- `manage_discount_codes`
- `get_store_buy_link`
- `check_client_balances`
- `charge_stored_payment`
- `record_payment`
- `manage_invoices`
- `record_expense`
- `run_financial_report`
- `run_general_report`
- `send_sms`
- `share_document`
- `edit_email_template`
- `edit_signup_form`

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.

TDQS

A3.7/5.0

Scored across 7 tools

Disambiguation5/5

Each tool targets a clearly distinct step in the browser automation loop: guide (instructions), status (account check), open (launch), read (inspect), click (interact), type (input), close (teardown). There is no meaningful overlap, and the descriptions reinforce the sequence. An agent can easily select the right tool.

Naming Consistency5/5

All seven tools share the ptminder_ prefix and use short snake_case action words. The convention is uniform and readable throughout, with only a trivial noun-vs-verb distinction between guide/status and open/read/click/type/close.

Tool Count5/5

Seven tools is well-scoped for a browser automation server. The set covers the full interaction loop plus onboarding (guide) and account validation (status), with no redundant tools.

Completeness4/5

The open/read/click/type/close cycle provides a complete CRUD-style interaction loop for working on PTminder pages via a browser. Minor gaps remain, such as scrolling, screenshots, or explicit dropdown-select handling, but an agent can work around these through clicking and reading.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues