Skip to main content
Glama
Hevy Coach MCP Server

Hevy Coach MCP Server

README.md
# Hevy Coach MCP server

Connect Hevy Coach to ChatGPT, Claude and any AI agent through Cotlet.dev. Work in your own coach account with 13 hosted operations for client activity, programs, exercises, progress pictures, chat, teams and leads. Write actions ask for approval by default.

## What you can ask

> Find clients who were inactive last week.

> Compare progress pictures for Jordan Example before a check-in.

> Draft a check-in message for Taylor Demo and show it for approval before sending.

## 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 Hevy Coach 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 hevy_coach_agent.py serve
```

Or with Docker:

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

Tools: `hevy_coach_guide`, `hevy_coach_status`, `hevy_coach_open`, `hevy_coach_read`, `hevy_coach_click`, `hevy_coach_type`, `hevy_coach_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 hevy_coach_agent.py connect   # ready config for ChatGPT, Claude Code, Cursor
python3 hevy_coach_agent.py status    # is Hevy Coach ready in your Cotlet.dev account
python3 hevy_coach_agent.py guide     # Hevy Coach screens and sign-in link
python3 hevy_coach_agent.py read      # open Hevy Coach, read the page, close the browser
python3 hevy_coach_agent.py tools     # list Cotlet.dev tools
python3 hevy_coach_agent.py serve     # start the stdio MCP server (same as no argument)
```

## Questions from Hevy Coach users

**Which account should I connect?**

Sign in to your own coach account at app.hevycoach.com in the Cotlet Cloud Browser.

**Which actions ask for approval?**

The eight write operations ask for approval by default. Five read operations cover the dashboard, clients, progress pictures and libraries.

**Is Cotlet affiliated with Hevy Coach?**

No. Cotlet.dev is independent and not affiliated with Hevy Coach.

## Learn more

- [Hevy Coach integration and hosted tools](https://cotlet.dev/integrations/hevy-coach-api-mcp-server)

---

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

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

## Workflows on the hosted integration

The live integration page documents these 13 operations:

- `view_dashboard`
- `list_clients`
- `view_progress_pictures`
- `invite_client`
- `remove_client`
- `view_program_library`
- `browse_exercise_library`
- `create_program`
- `create_custom_exercise`
- `assign_program`
- `send_message`
- `manage_team`
- `manage_public_invite`

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.