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

Connect Zenoti to ChatGPT, Claude and other AI agents through Cotlet.dev. Work with appointments, guest conversations, reviews and reports in your signed-in Zenoti account. Writes ask for approval by default.

## What you can ask

> Show appointments for tomorrow at my center.

> Draft replies to unread guest conversations for my approval.

> Run the employee commission report for this month.

## 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/connect`, then sign in with Cotlet.dev. No API key needed.

### Claude

Settings > Connectors > Add custom connector: `https://cotlet.dev/mcp/v1/connect`, then sign in with Cotlet.dev.

### Codex

```toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
```

### 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 ${env:COTLET_API_KEY}"
      }
    }
  }
}
```

## Run it locally (stdio)

This repo is a real MCP server. It speaks MCP over stdio, lists its Zenoti 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 zenoti_agent.py serve
```

Or with Docker:

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

Tools: `zenoti_guide`, `zenoti_status`, `zenoti_open`, `zenoti_read`, `zenoti_click`, `zenoti_type`, `zenoti_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 zenoti_agent.py connect   # ready config for Claude Code, Cursor, ChatGPT
python3 zenoti_agent.py status    # is Zenoti ready in your Cotlet.dev account
python3 zenoti_agent.py guide     # Zenoti screens and sign-in link
python3 zenoti_agent.py read      # open Zenoti, read the page, close the browser
python3 zenoti_agent.py tools     # list Cotlet.dev tools
python3 zenoti_agent.py serve     # start the stdio MCP server (same as no argument)
```

## Questions from Zenoti users

**Do I need the Zenoti API package?**

Cotlet.dev works through your employee login in a Cloud Browser. The official Zenoti API is a separate option enabled through your Customer Success Manager.

**What needs my approval?**

Write operations ask for approval by default. Review each change before confirming it.

**Is this affiliated with Zenoti?**

No. Cotlet.dev is unofficial and not affiliated with Zenoti.

## Learn more

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

---

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

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

## Workflows on the hosted integration

The live integration page documents these 20 operations:

- `view_appointment_book`
- `manage_appointments`
- `manage_queue`
- `manage_classes`
- `configure_kiosk`
- `get_guest_summary`
- `manage_guests`
- `manage_loyalty_points`
- `manage_conversations`
- `send_broadcast`
- `manage_reviews`
- `manage_smartbot_faqs`
- `make_sale`
- `manage_marketing`
- `manage_inventory`
- `manage_employee_schedule`
- `run_report`
- `view_hyperconnect_reports`
- `view_growth_dashboard`
- `view_fitness_dashboard`

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

A3.6/5.0

Scored across 7 tools

Disambiguation5/5

Each tool maps to a distinct browser-session operation: setup guidance, account readiness, opening a page, reading the page, clicking, typing, and closing. The only mild overlap is that both zenoti_guide and zenoti_status are pre-work steps, but their purposes are clearly different.

Naming Consistency4/5

All tools use a consistent zenoti_ prefix and snake_case style, making the set easy to scan. There is a minor deviation because guide and status are nouns while the remaining tools are verbs, but the pattern remains predictable.

Tool Count5/5

Seven tools is a well-scoped set for browser-based interaction with Zenoti. Each tool has a clear role in the session lifecycle and none feels redundant.

Completeness4/5

The surface covers the core browser automation lifecycle: open, inspect, interact, and close. Minor gaps such as explicit navigation/back or keyboard submission are not present, but click and type likely let agents work around them.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues