ui-vision-mcp

UI Vision MCP Server

MCP Server for multi-model vision analysis. Enables Claude Code to analyze images using external vision AI models (GLM, Gemini, GPT-4o, etc.).

Installation

npm install
npm run build

Configuration

Create config file at ~/.config/ui-vision-mcp/config.json:

{
  "models": [
    {
      "name": "glm",
      "baseUrl": "https://open.bigmodel.cn/api/paas/v4",
      "apiKey": "${GLM_API_KEY}",
      "model": "glm-4.6v-flash"
    },
    {
      "name": "gemini",
      "baseUrl": "https://generativelanguage.googleapis.com/v1beta/openai",
      "apiKey": "${GEMINI_API_KEY}",
      "model": "gemini-2.5-flash"
    }
  ]
}

Environment variables in ${VAR_NAME} format are automatically expanded.

Custom Config Path

Set VISION_CONFIG environment variable to use a different config file path.

Claude Code Setup

Add to ~/.claude/settings.json:

{
  "mcpServers": {
    "ui-vision": {
      "command": "npx",
      "args": ["ui-vision-mcp"],
      "env": {
        "VISION_CONFIG": "/path/to/custom/config.json",
        "GLM_API_KEY": "your-api-key"
      }
    }
  }
}

Tool: analyze_image

Analyzes images using configured vision models in parallel.

Parameters:

Name	Type	Description
images	string[]	Image paths (local files, URLs, or base64 data)
prompt	string	Analysis instruction

Example:

{
  "images": ["./design.png", "./screenshot.png"],
  "prompt": "Compare these two images. The first is the design, the second is the implementation. List differences in layout, spacing, and colors."
}

Response:

{
  "results": [
    { "model": "glm-4.6v-flash", "result": "Analysis from GLM..." },
    { "model": "gemini-2.5-flash", "result": "Analysis from Gemini..." }
  ]
}

Supported Providers

Provider	Base URL	Model Examples
GLM	https://open.bigmodel.cn/api/paas/v4	glm-4.6v-flash
Gemini	https://generativelanguage.googleapis.com/v1beta/openai	gemini-2.5-flash
OpenAI	https://api.openai.com/v1	gpt-4o
OpenRouter	https://openrouter.ai/api/v1	Various

Any OpenAI-compatible API endpoint can be used.