# mcp-vision

GitHub: lbyxunxunnini/mcp-vision · License: MIT · 当前版本：**v0.1.0**

MCP Server for image recognition, powered by Kimi K2.5 (Infini-AI).

## Features

- `recognize_image` - Recognize and describe images using multimodal AI

## Prerequisites

- Node.js >= 18
- An Infini-AI API key (https://cloud.infini-ai.com)

## Installation

```bash
# 1. Extract the archive
tar -xzf mcp-vision.tar.gz
cd mcp-vision

# 2. Install dependencies and build
npm install && npm run build
```

## Claude Code Configuration

Add the following to your Claude Code settings (`~/.claude/settings.json` or project `.claude/settings.json`):

```json
{
  "mcpServers": {
    "vision": {
      "command": "node",
      "args": ["/path/to/mcp-vision/dist/index.js"],
      "env": {
        "INFINI_API_KEY": "your-api-key-here"
      }
    }
  }
}
```

Replace `/path/to/mcp-vision` with the actual path where you extracted the project.

## Usage

Once configured, the `mcp__vision__recognize_image` tool is available in Claude Code.

### Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `image_path` | string | Yes | Absolute path to the local image file |
| `prompt` | string | No | Custom instruction, e.g. "extract all text", "describe the UI layout" |

### Supported Formats

PNG, JPG, JPEG, GIF, WebP, BMP

### Example

```
请识别这张图片: /Users/me/Desktop/screenshot.png
```

Claude Code will automatically call the MCP tool to process the image.

## Environment Variables

| Variable | Description |
|----------|-------------|
| `INFINI_API_KEY` | **Required.** Your Infini-AI API key |