Skip to main content

OpenAI API Integration

Use the Json2doc MCP server with OpenAI's API to generate documents 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": "json2doc",
            "server_url": "https://mcp.json2doc.com/mcp",
            "require_approval": "never",
            "headers": {
                "x-api-key": "your-json2doc-api-key"
            }
        }
    ],
    input="Create a PDF document with a title 'Project Report' and a paragraph about our Q4 results.",
)

print(response.output_text)
warning

Replace your-openai-api-key and your-json2doc-api-key with your actual API keys.

Configuration Options​

{
    "type": "mcp",                        # Required: Must be "mcp"
    "server_label": "json2doc",           # Label for the MCP server
    "server_url": "https://mcp.json2doc.com/mcp",  # MCP server endpoint
    "require_approval": "never",          # "never", "always", or "auto"
    "headers": {
        "x-api-key": "your-json2doc-api-key"  # Your Json2doc 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 Invoice​

from openai import OpenAI

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

invoice_data = {
    "customer": "Acme Corp",
    "amount": 2500.00,
    "items": [
        {"description": "Consulting Services", "amount": 2000.00},
        {"description": "Support Package", "amount": 500.00}
    ]
}

response = client.responses.create(
    model="gpt-4o",
    tools=[
        {
            "type": "mcp",
            "server_label": "json2doc",
            "server_url": "https://mcp.json2doc.com/mcp",
            "require_approval": "never",
            "headers": {
                "x-api-key": "your-json2doc-api-key"
            }
        }
    ],
    input=f"Create a professional invoice PDF for {invoice_data['customer']} "
          f"with total amount ${invoice_data['amount']}. "
          f"Include these items: {invoice_data['items']}",
)

print(response.output_text)

Example 2: Batch Document Generation​

from openai import OpenAI

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

customers = ["Acme Corp", "TechStart Inc", "Global Solutions"]

for customer in customers:
    response = client.responses.create(
        model="gpt-4o",
        tools=[
            {
                "type": "mcp",
                "server_label": "json2doc",
                "server_url": "https://mcp.json2doc.com/mcp",
                "require_approval": "never",
                "headers": {
                    "x-api-key": "your-json2doc-api-key"
                }
            }
        ],
        input=f"Generate a monthly status report PDF for {customer}. "
              f"Include sections for: Overview, Key Metrics, Achievements, Next Steps.",
    )
    
    print(f"Generated report for {customer}: {response.output_text}")

Troubleshooting​

Authentication Errors​

Solutions:

  • Verify your Json2doc 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.json2doc.com/mcp
  • Check your internet connection
  • Ensure firewall allows the connection

Rate Limiting​

Solutions:

  • Check your Json2doc plan limits in the dashboard
  • Implement exponential backoff in your code
  • Monitor your usage