IMPORTANT ASYNCHRONOUS TASK WORKFLOW
- Call this MCP generation tool once and read taskId from structuredContent.
- Do not call generation again while pending or running.
- Query nexscope_media_task_result with this skill slug, the exact taskId, and the same bearer credential using progressive backoff.
Multimodal AI
Smart Multi-Image Editing API v3
Fuse multiple images with an instruction prompt.
MCP tool name
nexscope_smart_multi_image_editing_v3MCP endpoint
https://api.nexscope.ai/mcpJSON-RPC method
tools/callAuthentication
Use OAuth 2.1 Authorization Code with PKCE and the mcp:tools scope. API keys remain supported as a compatibility option.
Authorization: Bearer nk-xxxxxxxxxxxxxxxxxIf authentication fails, ask the user to open API Access and copy a valid key.
Call this MCP tool
Initialize an MCP 2025-11-25 Streamable HTTP session at https://api.nexscope.ai/mcp, then use tools/call.
{
"jsonrpc": "2.0",
"id": "smart-multi-image-editing-v3-1",
"method": "tools/call",
"params": {
"name": "nexscope_smart_multi_image_editing_v3",
"arguments": {
"aspectRatio": "1:1",
"imageList": [
"https://example.com/product.jpg",
"https://example.com/model-reference.jpg"
],
"needOptimize": true,
"outputNum": 1,
"prompt": "combine the product with the model in a clean studio scene",
"provider": "BANANA_PRO",
"quality": "medium",
"resolution": "1K",
"supplyType": "stable",
"template": "outfit-fusion"
}
}
}MCP 2025-11-25 · Streamable HTTPProgress is delivered on the original POST SSE response. GET SSE carries notifications; reconnecting must query existing asynchronous work rather than submit again.
Asynchronous task workflow
- 1. Create once
Keep the returned taskId.
- 2. Query with backoff
Use nexscope_media_task_result after 5 seconds, then 10, 20, and 30 seconds.
- 3. Use final result
Stop at success, failure, or timeout.
{
"jsonrpc": "2.0",
"id": "smart-multi-image-editing-v3-result-1",
"method": "tools/call",
"params": {
"name": "nexscope_media_task_result",
"arguments": {
"skillSlug": "smart-multi-image-editing-v3",
"taskId": "TASK_ID_FROM_THE_GENERATION_RESULT"
}
}
}Arguments
| Name | Type | Required | Description |
|---|---|---|---|
imageList | array | required | Public image URLs to combine or reference. Provide no more than 6 JPG, JPEG, PNG, or WEBP images; each image must be at most 10 MB and between 800 and 4096 pixels. Example: [
"https://example.com/product.jpg",
"https://example.com/model-reference.jpg"
] |
provider | string | required | Image model. Available options
Example: BANANA_PRO |
prompt | string | optional | Optional fusion instruction, up to 600 characters. Example: combine the product with the model in a clean studio scene |
outputNum | integer | optional | Number of images to generate. Defaults to 1. Example: 1 |
resolution | string | optional | Target resolution preset. Example: 1K |
aspectRatio | string | optional | Target aspect ratio. Example: 1:1 |
supplyType | string | optional | Generation route. Defaults to stable. Available options
Example: stable |
needOptimize | boolean | optional | Whether the prompt should be optimized upstream. Example: true |
template | string | optional | Optional fusion template. Available options
Example: outfit-fusion |
quality | string | optional | GPT Image quality only. Defaults to medium. Available options
Example: medium |
Response fields
Treat structuredContent as the programmatic API response payload.
| Name | Type | Required | Description |
|---|---|---|---|
code | integer | required | 0 means accepted or successful; nonzero is a platform error. |
cost | string | required | Elapsed milliseconds, never credits; -1 outside web requests. |
data | any | required | Data value used by this API operation. |
msg | string | null | required | Msg value used by this API operation. |
time | string | required | Server local time: yyyy-MM-dd HH:mm:ss. |
traceId | string | null | required | Trace id value used by this API operation. |
ts | string | required | Epoch milliseconds. |
Any of option 1 — requires taskId, status, result
| Name | Type | Required | Description |
|---|---|---|---|
data | object | required | Data value used by this API operation. |
data.result | any | required | Completed generation output retained from the task result. Fields vary by capability; generated resources use Nexscope-hosted URLs and any count represents charged Nexscope credits. This is the business output, not a task creation receipt. |
data.status | string | required | Status value used by this API operation. Allowed: PENDING, RUNNING, SUCCEEDED, FAILED, TIMEOUT |
data.taskId | string | required | Task id value used by this API operation. |
Any of option 1
| Name | Type | Required | Description |
|---|---|---|---|
data.result | object | required | Completed generation output retained from the task result. Fields vary by capability; generated resources use Nexscope-hosted URLs and any count represents charged Nexscope credits. This is the business output, not a task creation receipt. |
Any of option 2
| Name | Type | Required | Description |
|---|---|---|---|
data.result | null | required | Completed generation output retained from the task result. Fields vary by capability; generated resources use Nexscope-hosted URLs and any count represents charged Nexscope credits. This is the business output, not a task creation receipt. |
Any of option 2
| Name | Type | Required | Description |
|---|---|---|---|
data | null | required | Data value used by this API operation. |
Examples
Example arguments
{
"aspectRatio": "1:1",
"imageList": [
"https://example.com/product.jpg",
"https://example.com/model-reference.jpg"
],
"needOptimize": true,
"outputNum": 1,
"prompt": "combine the product with the model in a clean studio scene",
"provider": "BANANA_PRO",
"quality": "medium",
"resolution": "1K",
"supplyType": "stable",
"template": "outfit-fusion"
}Example structuredContent
{
"code": 0,
"cost": "-1",
"data": {
"result": null,
"status": "PENDING",
"taskId": "example-task"
},
"msg": null,
"time": "2026-01-01 00:00:00",
"traceId": null,
"ts": "0"
}