Skip to main content

OpenAI API Integration

Use the JsonCut MCP server with OpenAI's API to generate images and videos programmatically.

Prerequisites​

Installation​

pip install openai

Basic Usage​

from openai import OpenAI

client = OpenAI(api_key="your-openai-api-key")

response = client.responses.create(
    model="gpt-4o",
    tools=[
        {
            "type": "mcp",
            "server_label": "jsoncut",
            "server_url": "https://mcp.jsoncut.com/mcp",
            "require_approval": "never",
            "headers": {
                "x-api-key": "your-jsoncut-api-key"
            }
        }
    ],
    input="Create a social media image with the text 'New Product Launch' on a gradient background.",
)

print(response.output_text)
warning

Replace your-openai-api-key and your-jsoncut-api-key with your actual API keys.

Configuration Options​

{
    "type": "mcp",                        # Required: Must be "mcp"
    "server_label": "jsoncut",           # Label for the MCP server
    "server_url": "https://mcp.jsoncut.com/mcp",  # MCP server endpoint
    "require_approval": "never",          # "never", "always", or "auto"
    "headers": {
        "x-api-key": "your-jsoncut-api-key"  # Your JsonCut API key
    }
}

Approval Modes:

  • "never" - AI uses tools without approval (recommended for automation)
  • "always" - AI asks for approval before using tools
  • "auto" - AI decides when to ask for approval

Examples​

Example 1: Generate Social Media Image​

from openai import OpenAI

client = OpenAI(api_key="your-openai-api-key")

image_data = {
    "title": "Summer Sale",
    "discount": "50% OFF",
    "background": "gradient"
}

response = client.responses.create(
    model="gpt-4o",
    tools=[
        {
            "type": "mcp",
            "server_label": "jsoncut",
            "server_url": "https://mcp.jsoncut.com/mcp",
            "require_approval": "never",
            "headers": {
                "x-api-key": "your-jsoncut-api-key"
            }
        }
    ],
    input=f"Create a promotional image with title '{image_data['title']}' "
          f"and discount text '{image_data['discount']}' "
          f"on a {image_data['background']} background.",
)

print(response.output_text)

Example 2: Batch Image Generation​

from openai import OpenAI

client = OpenAI(api_key="your-openai-api-key")

products = ["Product A", "Product B", "Product C"]

for product in products:
    response = client.responses.create(
        model="gpt-4o",
        tools=[
            {
                "type": "mcp",
                "server_label": "jsoncut",
                "server_url": "https://mcp.jsoncut.com/mcp",
                "require_approval": "never",
                "headers": {
                    "x-api-key": "your-jsoncut-api-key"
                }
            }
        ],
        input=f"Generate a product showcase image for {product}. "
              f"Include product name, features, and a call-to-action button.",
    )
    
    print(f"Generated image for {product}: {response.output_text}")

Troubleshooting​

Authentication Errors​

Solutions:

  • Verify your JsonCut API key in the dashboard
  • Check the header name is x-api-key
  • Ensure no extra spaces in the key
  • Verify the key hasn't expired

Connection Issues​

Solutions:

  • Verify the URL: https://mcp.jsoncut.com/mcp
  • Check your internet connection
  • Ensure firewall allows the connection

Rate Limiting​

Solutions:

  • Check your JsonCut plan limits in the dashboard
  • Implement exponential backoff in your code
  • Monitor your usage