mcp-vision-google mcp

v1.0.0 · MCP Tool · ai · registry.pascalai.org

Analyze images using Google Cloud Vision API: label detection, OCR, face/logo/landmark detection and safe search.

googlevisionocrimageanalysiscloud

Input Parameters

Parameter	Type	Description
credentials_jsonrequired	string
operationrequired	string	One of: `label_detection`, `text_detection`, `document_text`, `face_detection`, `logo_detection`, `landmark_detection`, `safe_search`, `object_detection`, `image_properties`, `crop_hints`.
image_urloptional	string
image_pathoptional	string
image_base64optional	string
max_resultsoptional	integer	Default: `10`.
language_hintsoptional	array[string]

Output Fields

Field	Type	Description
operation	string
labels	array[object]
text	string
faces	array[object]
logos	array[object]
objects	array[object]
safe_search	object

Examples

Detect labels in image

// Input
{
  "credentials_json": "/sa.json",
  "operation": "label_detection",
  "image_url": "https://example.com/dog.jpg",
  "max_results": 5
}

// Output
{
  "operation": "label_detection",
  "labels": [
    {
      "description": "Dog",
      "score": 0.98
    },
    {
      "description": "Animal",
      "score": 0.95
    }
  ]
}

Install & Discovery

Install

ppm install mcp-vision-google

Get JSON Schema

GET /v1/packages/mcp-vision-google/1.0.0/schema

Discover by keyword

GET /v1/mcp/discover?q=google

Discovery hint: Install with ppm install mcp-vision-google or invoke remotely via POST /v1/invoke/mcp-vision-google on the MCP Service.

PascalAI Usage

uses toolslib;
var Tool := LoadTool('mcp-vision-google');
var R := Tool.Call(JsonObj([]));
Writeln(R.ToJSON);