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

Connect SalonBiz to ChatGPT, Claude, Codex and Claude Code through Cotlet.dev. Read appointments, tickets, inventory, payments and reports in your own signed-in salon account. Booking changes, online booking settings and email campaigns ask for your approval by default.

## What you can ask

> List tomorrow's unconfirmed appointments.

> List low-stock products before ordering.

> Draft an email campaign for lapsed clients and show it before scheduling.

## 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`. 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 SalonBiz 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 salonbiz_agent.py serve
```

Or with Docker:

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

Tools: `salonbiz_guide`, `salonbiz_status`, `salonbiz_open`, `salonbiz_read`, `salonbiz_click`, `salonbiz_type`, `salonbiz_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 salonbiz_agent.py connect   # ready config for Claude Code, Cursor, ChatGPT
python3 salonbiz_agent.py status    # is SalonBiz ready in your Cotlet.dev account
python3 salonbiz_agent.py guide     # SalonBiz screens and sign-in link
python3 salonbiz_agent.py read      # open SalonBiz, read the page, close the browser
python3 salonbiz_agent.py tools     # list Cotlet.dev tools
python3 salonbiz_agent.py serve     # start the stdio MCP server (same as no argument)
```

## Questions from SalonBiz users

**How do I connect my account?**

Request access at https://cotlet.dev/signup?app=salonbiz, sign in to SalonBiz in your Cotlet.dev Cloud Browser and enable it for agents.

**Can the agent take payments?**

No. Tickets and payments are read only. Checkout, refunds and card charges stay with your team in SalonBiz.

**Can I review changes?**

Booking changes, online booking settings and campaigns ask for confirmation by default. You can change approval settings per tool.

**Is Cotlet.dev affiliated with SalonBiz?**

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

## Learn more

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

---

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

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

## Workflows on the hosted integration

Examples documented on the live integration page:

- `manage_appointment_book`
- `manage_online_booking`
- `view_point_of_sale`
- `view_inventory`
- `view_salon_payments`
- `view_reporting`
- `manage_marketing`

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 has a distinct role in the browser-automation workflow: guide, readiness check, open, read, click, type, and close. There is little risk of confusing one action with another, and the descriptions reinforce the intended sequence.

Naming Consistency5/5

All tools use the same salonbiz_ prefix and lowercase snake_case action names. The pattern is predictable and easy to scan.

Tool Count5/5

Seven tools is well-scoped for a browser-assisted domain workflow. The set includes setup, interaction, reading, typing, and cleanup without unnecessary extras.

Completeness4/5

The core lifecycle is covered: check readiness, open a page, read it, click and type, then close the session. Minor gaps exist for common browser needs like explicit navigation/back, scrolling, or keyboard actions, but most SalonBiz tasks can likely be handled through click and type.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues