Claude MCP Integration

Use ProductAI as an MCP server with Claude Desktop and other MCP-compatible AI assistants.

Overview

The Model Context Protocol (MCP) allows AI assistants like Claude to interact with external tools and services. The ProductAI MCP server enables Claude to generate product images directly in your conversations.

View on GitHub

Features

Generate product images through natural conversation
Upload and manage assets
Use templates for consistent styling
Check job status and retrieve results

Installation

1. Install the MCP server

npm install -g @shapestudio/productai-mcp

2. Configure Claude Desktop

Add the following to your Claude Desktop configuration file:

// macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
// Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "productai": {
      "command": "productai-mcp",
      "env": {
        "PRODUCTAI_API_KEY": "your-api-key-here"
      }
    }
  }
}

3. Restart Claude Desktop

After updating the configuration, restart Claude Desktop to load the ProductAI MCP server.

Available Tools

productai_generate

Generate a product image with AI-powered backgrounds.

Parameters: image_url, prompt, model, preset_id, num_images, aspect_ratio

productai_upload_asset

Upload a product image for later use.

Parameters: url, name, tags

productai_list_assets

List all uploaded assets.

Parameters: limit, status

productai_get_job

Get the status and results of a generation job.

Parameters: job_id

productai_list_templates

List available templates/presets.

Parameters: category, limit

Example Usage

Once configured, you can ask Claude to generate product images naturally:

"Generate a product image for this sneaker on a marble table with soft lighting: https://example.com/sneaker.jpg"

Claude will use the ProductAI MCP server to generate the image and return the results.

Environment Variables

Variable	Required	Description
`PRODUCTAI_API_KEY`	Yes	Your ProductAI API key
`PRODUCTAI_BASE_URL`	No	Custom API base URL (default: https://api.productai.photo)

Get API Key →API Reference →All Integrations →