Multimodal AI

Multimodal Image Recognition API MCP Tool

Analyze and extract information from images using multimodal AI recognition. When a user provides an image URL and asks questions about its visual content, this API should be triggered

MCP tool name

nexscope_multimodal_image_recognition_api

Equivalent REST API path

https://claw-callback.nexscope.ai/api/skill-api/v1/skills/multimodal-image-recognition-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": "multimodal-image-recognition-api-1",
  "method": "tools/call",
  "params": {
    "name": "nexscope_multimodal_image_recognition_api",
    "arguments": {
      "requirement": "Describe the product shown in this image",
      "imageUrl": "https://m.media-amazon.com/images/I/61v6nYvQ7+L._AC_SL1500_.jpg"
    }
  }
}

REST API equivalent

POST https://claw-callback.nexscope.ai/api/skill-api/v1/skills/multimodal-image-recognition-api/run

Canonical detail URL

https://www.nexscope.ai/mcp-map/multimodal-image-recognition-api

Arguments

Name	Type	Required	Meaning
`imageUrl`	`string`	required	Image URL. Supported formats: JPG, JPEG, PNG, GIF, WEBP, and BMP. Maximum 1,000 characters Example: https://m.media-amazon.com/images/I/61v6nYvQ7+L._AC_SL1500_.jpg
`requirement`	`string`	optional	User intent describing what to recognize or analyze in the image. Default: describe the contents of this image. Maximum 1,000 characters Example: {}

Response fields

Treat structuredContent as the programmatic API response payload.

Name	Type	Required	Meaning
`text`	`string`	optional	Text result of the image analysis Example: {}
`stdout`	`string`	optional	Standard output content Example: {}
`status`	`string`	optional	Response status indicator Example: {}
`type`	`string`	optional	Component type Example: {}
`costToken`	`integer`	optional	Tokens consumed Example: 1
`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: {}
`message`	`string`	optional	Provider-specific message. 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: {}
`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

{
  "requirement": "Describe the product shown in this image",
  "imageUrl": "https://m.media-amazon.com/images/I/61v6nYvQ7+L._AC_SL1500_.jpg"
}

Example structuredContent

{
  "costToken": 1
}