Submit Generation Async

Immutable Catalog Entry

This descriptor comes from the active versioned Portal catalog.

WRITEleonardo-ai.leonardo_submit_generation_async

• Contract tier: agent_ready
• Risk: write
• Catalog version: leonardo-ai-2026.07.12.1
• Descriptor hash: 4386a5375c4926eb5849c9d0877195d60224577cdf062656ac09f38a9ba1eee3

Submit a Leonardo job, store its ID locally, and rely on webhook completion. Requires the request-scoped x-leonardo-api-key Portal field and contacts Leonardo.Ai.

Request Body

{
  "jsonrpc": "2.0",
  "id": "leonardo-ai-leonardo-submit-generation-async-example",
  "method": "tools/call",
  "params": {
    "name": "leonardo-ai.leonardo_submit_generation_async",
    "arguments": {
      "body": "",
      "mode": "v2_media",
      "request_body": ""
    }
  }
}

Arguments Schema

{
  "type": "object",
  "properties": {
    "body": {
      "anyOf": [
        {
          "type": "object",
          "additionalProperties": true
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Leonardo request body using provider parameter names exactly. For v1 image generation use fields such as prompt, modelId, width, height, num_images, alchemy, ultra, public, imagePrompts, init_image_id, or isInitImage. For v2 generation use model, public, and parameters."
    },
    "mode": {
      "enum": [
        "v2_media",
        "v1_image",
        "image_to_video",
        "text_to_video",
        "svd_motion",
        "video_upscale"
      ],
      "type": "string",
      "default": "v2_media",
      "description": "Leonardo async generation endpoint family to submit."
    },
    "request_body": {
      "anyOf": [
        {
          "type": "object",
          "additionalProperties": true
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Alias for body. Use when an agent has a planned request_body from a planning tool."
    }
  },
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "description": "Leonardo MCP result. ok=false, provider_ok=false, a failed status, or an error field represents a semantic failure even when transport delivery succeeded.",
  "additionalProperties": true
}

Code Examples

cURL

curl -X POST 'https://portal.madpanda3d.com/api/mcp' \
  -H 'Authorization: Bearer mad_live_***' \
  -H 'Content-Type: application/json' \
  -d '{
  "jsonrpc": "2.0",
  "id": "leonardo-ai-leonardo-submit-generation-async-example",
  "method": "tools/call",
  "params": {
    "name": "leonardo-ai.leonardo_submit_generation_async",
    "arguments": {
      "body": "",
      "mode": "v2_media",
      "request_body": ""
    }
  }
}'

Node.js

const response = await fetch('https://portal.madpanda3d.com/api/mcp', {
  method: 'POST',
  headers: {
    Authorization: 'Bearer mad_live_***',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "jsonrpc": "2.0",
  "id": "leonardo-ai-leonardo-submit-generation-async-example",
  "method": "tools/call",
  "params": {
    "name": "leonardo-ai.leonardo_submit_generation_async",
    "arguments": {
      "body": "",
      "mode": "v2_media",
      "request_body": ""
    }
  }
}),
});
const data = await response.json();
console.log(data);

Python

import requests

url = 'https://portal.madpanda3d.com/api/mcp'
headers = {
    'Authorization': 'Bearer mad_live_***',
    'Content-Type': 'application/json',
}
payload = {
  "jsonrpc": "2.0",
  "id": "leonardo-ai-leonardo-submit-generation-async-example",
  "method": "tools/call",
  "params": {
    "name": "leonardo-ai.leonardo_submit_generation_async",
    "arguments": {
      "body": "",
      "mode": "v2_media",
      "request_body": ""
    }
  }
}
response = requests.post(url, headers=headers, json=payload, timeout=60)
print(response.json())

Example Responses

200 Success

{
  "ok": true,
  "message": "Tool leonardo-ai.leonardo_submit_generation_async executed successfully.",
  "note": "Response shape varies by MCP tool. Inspect live responses for exact fields."
}

502 Upstream Error

{
  "ok": false,
  "classification": "upstream_http_error",
  "message": "Upstream MCP returned a non-success status."
}