mcp-vision-openai mcp

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

Analyze images using OpenAI GPT-4V (Vision): describe, caption, OCR, detect objects and answer questions.

visionopenaigpt4vocrimageanalysis

Input Parameters

Parameter	Type	Description
api_keyrequired	string
modeloptional	string	Default: `gpt-4o`.
image_urloptional	string	Image URL or base64 data URI.
image_pathoptional	string	Local image file path.
promptrequired	string	Default: `Describe this image in detail.`.
systemoptional	string
max_tokensoptional	integer	Default: `1024`.
temperatureoptional	number	Default: `0.0`.
multiple_imagesoptional	array[string]	Multiple image URLs/paths.

Output Fields

Field	Type	Description
content	string
model	string
usage	object

Examples

Describe image content

// Input
{
  "api_key": "sk-xxx",
  "model": "gpt-4o",
  "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/1200px-Cat03.jpg",
  "prompt": "What animal is in this image and what is it doing?"
}

// Output
{
  "content": "The image shows a cat sitting on a surface, looking directly at the camera with alert eyes.",
  "model": "gpt-4o"
}

Install & Discovery

Install

ppm install mcp-vision-openai

Get JSON Schema

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

Discover by keyword

GET /v1/mcp/discover?q=vision

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

PascalAI Usage

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