npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@guorui99/vision-mcp

v1.0.1

Published

MCP server for image analysis - gives LLMs vision via external visual API

Readme

🖼️ Vision MCP

让没有原生识图能力的模型(如 DeepSeek)也能"看图"——通过调用外部视觉 API 获取图片的文字描述。

提供 MCP ServerCLI 两种使用方式。


MCP Server(推荐)

工具

| 工具 | 说明 | 注解 | |------|------|------| | vision_analyze | 分析图片 — 本地路径或 URL,1-5 张,自定义 prompt | 只读 | | vision_get_config | 查看当前 API 配置(Key 脱敏) | 只读 | | vision_update_config | 更新 API Key / 模型 / 地址 | — |

快速开始

# 1. 安装依赖
npm install

# 2. 构建
npm run build

# 3. 配置 MCP(在 Claude Desktop / claude.json 中添加)
{
  "mcpServers": {
    "vision": {
      "command": "npx",
      "args": ["-y", "@guorui99/vision-mcp"]
    }
  }
}

首次配置

启动后,通过 MCP 工具配置 API Key:

vision_update_config api_key="sk-xxx"

或直接编辑 config.json

{
  "base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
  "api_key": "你的API Key",
  "model": "qwen3.5-omni-plus",
  "language": "zh"
}

支持的视觉服务

| 服务 | 模型 | 备注 | |------|------|------| | 阿里云百炼(推荐) | qwen3.5-omni-plus | 新用户 100 万 token 免费 | | 阿里云百炼 | qwen-vl-max | 同上 | | OpenAI | gpt-4o-mini | 需海外支付 | | 其他 | 任何 OpenAI 兼容格式 | 改 base_url + model 名 |

支持格式

jpg, jpeg, png, gif, webp, bmp(单次最多 5 张,单文件最大 20MB)

工作原理

  1. 读取图片 → base64 编码
  2. 调用 OpenAI 兼容视觉 API
  3. 返回文字描述

CLI 模式(legacy)

# 单张图片
node scripts/vision.cjs photo.jpg "描述这张图片"

# 网络图片
node scripts/vision.cjs --url https://example.com/img.png "这是什么?"

# 多张图片
node scripts/vision.cjs img1.jpg img2.jpg "比较这两张图"

# 配置
node scripts/vision.cjs --setup
node scripts/vision.cjs --config

项目结构

vision-mcp/
├── src/                 # MCP Server 源码 (TypeScript)
├── dist/                # 编译产物
├── scripts/vision.cjs   # CLI 工具 (legacy)
├── config.json          # 共享配置文件
├── package.json
└── tsconfig.json

环境要求

  • Node.js >= 18
  • 视觉 API 的 Key(阿里云百炼 / OpenAI 等)