magicpixels_text_to_image
Create a Qwen image job from a text prompt.
Agents can call the same MagicPixels generation queue through `/v1/mcp`. The endpoint supports initialize, tools/list, and tools/call over JSON-RPC.
Create a Qwen image job from a text prompt.
Edit an uploaded asset or base64 image with a prompt.
Generate voice audio from text and return a pollable job.
Create a talking-avatar video from image and audio assets.
Fetch job status and result URLs.
curl -X POST https://api.magicpixels.ai/v1/mcp \
-H "Authorization: Bearer mp_live_xxx.yyy" \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list"
}'curl -X POST https://api.magicpixels.ai/v1/mcp \
-H "Authorization: Bearer mp_live_xxx.yyy" \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "magicpixels_text_to_image",
"arguments": {
"prompt": "Clean editorial product render on a steel desk"
}
}
}'