# Trainzilla Coach MCP server

> Lets an AI client manage fitness clients, workout plans, nutrition, habits, and billing via the Trainzilla GraphQL API.

- Repository: https://github.com/Trainzilla/tzilla-mcp
- Page: https://hostedmcp.org/servers/trainzilla/tzilla-mcp
- Transport: remote
- Stars: 0
- Latest version: 1.0.0

## Install

### Claude Code

```sh
claude mcp add --transport http tzilla-mcp https://api.tzilla.live/mcp
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "tzilla-mcp": {
      "url": "https://api.tzilla.live/mcp"
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "tzilla-mcp": {
      "type": "http",
      "url": "https://api.tzilla.live/mcp"
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"tzilla-mcp","type":"http","url":"https://api.tzilla.live/mcp"}'
```

### Codex

```sh
codex mcp add tzilla-mcp --url https://api.tzilla.live/mcp
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.tzilla-mcp]
url = "https://api.tzilla.live/mcp"
```

### Gemini CLI

```sh
gemini mcp add -s user --transport http tzilla-mcp https://api.tzilla.live/mcp
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "tzilla-mcp": {
      "url": "https://api.tzilla.live/mcp",
      "type": "http"
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `TZ_ACCESS_TOKEN` | no | no |  |
| `TZ_API_URL` | no | no |  |
| `TZ_REFRESH_TOKEN` | no | no |  |

## Tools (4)

- `calc_tdee`
- `calc_macros`
- `calc_1rm`
- `create_checkin`

## FAQ

### Are write operations safe from accidental changes?

Yes, all write tools are confirm-gated and return a preview unless you explicitly call them with the confirm flag set to true.

### Can the server perform fitness calculations?

Yes, it includes offline calculators for TDEE, macronutrient splits, and 1-rep-max suggestions without needing a network connection.
