mcp-vision mcp

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

Analyze images using multimodal LLMs via MakerAI. Describe scenes, answer visual questions, detect objects, extract text (OCR), compare images and generate structured data from visual content.

visionimagemultimodalocrdetectanalyze

MakerAI Pipeline

Input Parameters

ParameterTypeDescription
operationrequired string 'describe': general description; 'ask': answer a question about the image; 'ocr': extract all text; 'detect': list objects/people/elements; 'compare': compare two images; 'extract': extract structured data (tables, forms, etc.). One of: describe, ask, ocr, detect, compare, extract.
image_urloptional string URL of the image to analyze (http/https or data URI).
image_b64optional string Base64-encoded image (alternative to image_url).
image_b64_2optional string Second image for compare operation.
questionoptional string Question to answer about the image (ask, extract operations).
extract_schemaoptional object JSON schema defining the structure to extract from the image (extract operation).
modeloptional string Multimodal model. Examples: 'claude-sonnet-4-6', 'gpt-4o', 'gemini-2.0-flash'. Empty = router default.
detailoptional string Image analysis detail level. Default: 'auto'. One of: low, high, auto. Default: auto.

Output Fields

FieldTypeDescription
operation string
description string Image description (describe).
answer string Answer to the question (ask).
text string Extracted text content (ocr).
objects array[string] Detected elements (detect).
comparison string Comparison analysis (compare).
extracted object Structured data extracted per schema (extract).
model string
tokens_used integer

Examples

Extract text from a receipt image

// Input
{
  "operation": "ocr",
  "image_url": "https://example.com/receipt.jpg"
}

// Output
{
  "operation": "ocr",
  "text": "Store: MegaMart\nDate: 2025-03-14\nTotal: $47.32\nItems:\n- Milk $2.99\n- Bread $3.49",
  "model": "gpt-4o",
  "tokens_used": 312
}

Extract structured data from a form

// Input
{
  "operation": "extract",
  "image_url": "https://example.com/invoice.png",
  "extract_schema": {
    "type": "object",
    "properties": {
      "invoice_number": {
        "type": "string"
      },
      "total": {
        "type": "number"
      },
      "date": {
        "type": "string"
      }
    }
  }
}

// Output
{
  "extracted": {
    "invoice_number": "INV-2025-0042",
    "total": 1250.0,
    "date": "2025-03-14"
  }
}

Install & Discovery

Install

ppm install mcp-vision

Get JSON Schema

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

Discover by keyword

GET /v1/mcp/discover?q=vision
Discovery hint: Install with ppm install mcp-vision or invoke remotely via POST /v1/invoke/mcp-vision on the MCP Service.

PascalAI Usage

uses toolslib;
var Tool := LoadTool('mcp-vision');
var R := Tool.Call(JsonObj(['operation','describe','image_url','https://example.com/photo.jpg']));
Writeln(R['description']);