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

Connect Arcadina to ChatGPT, Claude and any AI agent through Cotlet.dev. The hosted integration documents 13 operations for orders, galleries, bookings, contracts, invoices and your website. By default, 11 write operations ask for approval.

## What you can ask

> Summarize new orders and client photo selections.

> List my session bookings.

> Show my client galleries.

## 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 Arcadina 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 arcadina_agent.py serve
```

Or with Docker:

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

Tools: `arcadina_guide`, `arcadina_status`, `arcadina_open`, `arcadina_read`, `arcadina_click`, `arcadina_type`, `arcadina_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 arcadina_agent.py connect   # ready config for ChatGPT, Claude, Claude Code and Cursor
python3 arcadina_agent.py status    # is Arcadina ready in your Cotlet.dev account
python3 arcadina_agent.py guide     # Arcadina screens and sign-in link
python3 arcadina_agent.py read      # open Arcadina, read the page, close the browser
python3 arcadina_agent.py tools     # list Cotlet.dev tools
python3 arcadina_agent.py serve     # start the stdio MCP server (same as no argument)
```

## Questions from Arcadina users

**Where do I sign in to Arcadina?**

Open https://www.arcadina.com/login in your Cotlet Cloud Browser and sign in to your own management panel.

**Which changes ask for approval?**

By default, 11 of the 12 write operations ask first. Applying a gallery watermark runs without approval, as does reading orders and selections.

**Is Cotlet affiliated with Arcadina?**

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

## Learn more

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

---

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

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

## Workflows on the hosted integration

The live integration page documents these 13 operations:

- `review_orders_and_selections`
- `create_client_gallery`
- `apply_gallery_watermarks`
- `manage_store_price_lists`
- `manage_session_bookings`
- `send_contract`
- `create_invoice`
- `manage_website_pages`
- `customize_website_design`
- `create_contact_form`
- `publish_blog_post`
- `manage_site_languages`
- `connect_google_reviews`

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.