Multimodal AI

AI Model Swap API MCP Tool

Generate model images by combining a source product image with a model head image, optional masks, scene references, and prompt guidance.

MCP tool name

nexscope_ai_model_swap_api

Equivalent REST API path

https://claw-callback.nexscope.ai/api/skill-api/v1/skills/ai-model-swap-api/run

JSON-RPC method

tools/call

Authentication

Send the user API key as a bearer token on every MCP JSON-RPC request.

Authorization: Bearer nk_xxxxxxxxxxxxxxxxx

If authentication is missing or invalid, ask the user to open API Access and copy a valid key before calling this tool.

Call this MCP tool

Use tools/call with the MCP tool name below. The arguments object should match the table on this page.

{
  "jsonrpc": "2.0",
  "id": "ai-model-swap-api-1",
  "method": "tools/call",
  "params": {
    "name": "nexscope_ai_model_swap_api",
    "arguments": {
      "imageUrl": "https://example.com/source-image.jpg",
      "modelHeadImageUrl": "https://example.com/model-reference.jpg",
      "imageSegUrl": "https://example.com/mask.png",
      "sceneImgUrl": "https://example.com/scene.jpg",
      "sceneStrength": 0.6,
      "modelPrompt": "natural studio model",
      "customPrompt": "clean ecommerce catalog photo",
      "customNegPrompt": "blur, distorted hands",
      "genOriRes": true,
      "realModel": true,
      "outputNum": 1
    }
  }
}

REST API equivalent

POST https://claw-callback.nexscope.ai/api/skill-api/v1/skills/ai-model-swap-api/run

Canonical detail URL

https://www.nexscope.ai/mcp-map/ai-model-swap-api

Asynchronous task workflow

This capability uses a create-and-query flow. Creating the task and retrieving its final generated resources are two connected requests.

1. Create onceCall the MCP tool once and keep the returned taskId.
2. Query with backoffCall nexscope_media_task_result with this skill slug and task ID. Wait at least 5 seconds first; while pending or running, back off at 5, 10, 20, then 30-second intervals.
3. Use final resultStop at a terminal status. Successful results contain Nexscope resource URLs and the actual charged-credit count.

MCP task result call

{
  "jsonrpc": "2.0",
  "id": "ai-model-swap-api-result-1",
  "method": "tools/call",
  "params": {
    "name": "nexscope_media_task_result",
    "arguments": {
      "skillSlug": "ai-model-swap-api",
      "taskId": "TASK_ID_FROM_THE_GENERATION_RESULT"
    }
  }
}

REST fallback

GET https://claw-callback.nexscope.ai/api/skill-api/v1/skills/ai-model-swap-api/tasks/{taskId}

Arguments

Name	Type	Required	Meaning
`imageUrl`	`string`	required	Public URL of the source product or outfit image. Example: https://example.com/source-image.jpg
`modelHeadImageUrl`	`string`	required	Public URL of the target model head image. Example: https://example.com/model-reference.jpg
`imageSegUrl`	`string`	optional	Optional segmentation mask URL for the source image. Example: https://example.com/mask.png
`sceneImgUrl`	`string`	optional	Optional scene reference image URL. Example: https://example.com/scene.jpg
`sceneStrength`	`number`	optional	Scene reference strength. Example: 0.6
`modelPrompt`	`string`	optional	Model appearance prompt. Example: natural studio model
`customPrompt`	`string`	optional	Positive generation prompt. Example: clean ecommerce catalog photo
`customNegPrompt`	`string`	optional	Negative prompt to avoid unwanted artifacts. Example: blur, distorted hands
`genOriRes`	`boolean`	optional	Whether to generate the original resolution. Example: true
`realModel`	`boolean`	optional	Whether to prefer a realistic model style. Example: true
`outputNum`	`integer`	optional	Number of images to generate. Example: 1

Response fields

Treat structuredContent as the programmatic API response payload.

Name	Type	Required	Meaning
`taskId`	`string`	required	Nexscope asynchronous task id used to query the generation result. Example: 6b3f1c61-1b7d-4a59-8a7d-3b23e4b0c9e2
`status`	`string`	required	Task status. Initial run returns PENDING; the query endpoint may return PENDING, RUNNING, SUCCESS, FAILED, or TIMEOUT. Example: PENDING
`message`	`string`	optional	User-facing task state message. Example: The task has been created. Use taskId to query the result.
`errcode`	`integer`	optional	Upstream status code returned by the provider. Example: {}
`errmsg`	`string`	optional	Upstream status message returned by the provider. Example: {}
`code`	`string`	optional	Provider-specific status code. Example: {}
`msg`	`string`	optional	Provider-specific status message. Example: {}
`type`	`string`	optional	Provider-specific render or payload type. Example: {}
`title`	`string`	optional	Provider-specific response title. Example: {}
`sourceType`	`string`	optional	Provider-specific source platform type. Example: {}
`sourceTool`	`string`	optional	Provider-specific source tool name. Example: {}
`costToken`	`integer`	optional	Token cost reported by the upstream provider. Example: {}
`costTime`	`integer`	optional	Execution time reported by the upstream provider. Example: {}
`page`	`integer`	optional	Current page returned by the upstream provider. Example: {}
`pageSize`	`integer`	optional	Page size returned by the upstream provider. Example: {}
`pageItemCount`	`integer`	optional	Item count on the current page returned by the upstream provider. Example: {}
`totalPage`	`integer`	optional	Total page count returned by the upstream provider. Example: {}
`dataSnapshotMonth`	`string`	optional	Data snapshot month returned by the upstream provider. Example: {}

Examples

Example arguments

{
  "imageUrl": "https://example.com/source-image.jpg",
  "modelHeadImageUrl": "https://example.com/model-reference.jpg",
  "imageSegUrl": "https://example.com/mask.png",
  "sceneImgUrl": "https://example.com/scene.jpg",
  "sceneStrength": 0.6,
  "modelPrompt": "natural studio model",
  "customPrompt": "clean ecommerce catalog photo",
  "customNegPrompt": "blur, distorted hands",
  "genOriRes": true,
  "realModel": true,
  "outputNum": 1
}

Example structuredContent

{
  "taskId": "6b3f1c61-1b7d-4a59-8a7d-3b23e4b0c9e2",
  "status": "PENDING",
  "message": "The task has been created. Use taskId to query the result."
}

IMPORTANT ASYNCHRONOUS TASK WORKFLOW