Skip to main content
Glama
README.md
# Coach Catalyst API and MCP server

Connect ChatGPT, Claude and any AI agent to your Coach Catalyst account through Cotlet.dev.

## What you can ask

> List clients who missed two check-ins this month.

> Draft a reply to the latest client message and wait for my approval.

> Add a new client and assign the beginner program.

> Summarise this week’s check-in forms by coach.

> Build a workout and set it to repeat next Monday.

## Connect in 2 minutes

Get your API key at https://cotlet.dev/app and export it as `COTLET_API_KEY`.

### Claude Code

```bash
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"
```

### ChatGPT

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

### 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 Coach Catalyst 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.

```json
{"mcpServers":{"coach-catalyst":{"command":"uvx","args":["coach-catalyst-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}
```

Or with Docker:

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

Tools: `coach_catalyst_guide`, `coach_catalyst_status`, `coach_catalyst_open`, `coach_catalyst_read`, `coach_catalyst_click`, `coach_catalyst_type`, `coach_catalyst_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:

```bash
pip install coach-catalyst-mcp        # or run it once: uvx coach-catalyst-mcp connect
coach-catalyst-mcp connect
```

Or straight from this repo:

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

## Questions from Coach Catalyst users

**Does Coach Catalyst have an API?**

Coach Catalyst has no public API. Cotlet.dev provides a hosted MCP server for your account.

**How do I connect Coach Catalyst to ChatGPT?**

Add https://cotlet.dev/mcp/v1 as a connector in ChatGPT and sign in with Cotlet.dev.

**Can Claude use Coach Catalyst?**

Yes. Add the same Cotlet.dev MCP URL in Claude and approve each client-facing change.

**Is there a Coach Catalyst MCP server?**

Cotlet.dev hosts an MCP server with 25 Coach Catalyst tools.

## Find it on

- [Coach Catalyst on Cotlet.dev](https://cotlet.dev/integrations/coach-catalyst-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=coach-catalyst)
- [All apps connected through Cotlet.dev](https://github.com/cotlet-connect)

---

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

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