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

deep-vision

v1.0.0

Published

MCP server for vision/image analysis — powered by Agnes-2.0-Flash with ModelScope Qwen fallback

Readme

deep-vision MCP Server

视觉分析 MCP 服务器 — 基于 Agnes-2.0-Flash 主模型 + Qwen3-VL (ModelScope) 备用模型自动切换。

支持本地图片和在线 URL,为 Claude Code 等 MCP 客户端提供视觉分析能力。

架构

用户请求 (图片 + 提示词)
  ↓
Agnes-2.0-Flash (主模型)
  ↓ 失败?
Qwen3-VL (备用, ModelScope)
  ↓
返回文本分析结果

安装

npm install -g deep-vision

环境变量

| 变量名 | 必填 | 说明 | |--------|------|------| | AGNES_API_KEY | ✅ | Agnes AI API Key,从 platform.agnes-ai.com 获取 | | AGNES_MODEL | ❌ | 主模型名称,默认 agnes-2.0-flash | | MODELSCOPE_TOKEN | ❌ | 魔搭社区 Token(备用模型),不设置则主模型失败时直接报错 | | MODELSCOPE_MODEL | ❌ | 备用模型名称,默认 Qwen/Qwen3-VL-30B-A3B-Instruct |

配置

在 Claude Code 的 MCP 配置中添加:

{
  "mcpServers": {
    "deep-vision": {
      "type": "stdio",
      "command": "deep-vision",
      "args": [],
      "env": {
        "AGNES_API_KEY": "sk-your-agnes-api-key",
        "AGNES_MODEL": "agnes-2.0-flash",
        "MODELSCOPE_TOKEN": "your-modelscope-token",
        "MODELSCOPE_MODEL": "Qwen/Qwen3-VL-30B-A3B-Instruct"
      }
    }
  }
}

提示:如果未配置 MODELSCOPE_TOKEN,服务仍可正常启动,仅主模型 Agnes 不可用时会报错。

工具

analyze_image

分析图片内容并提供详细描述。

| 参数 | 类型 | 必填 | 说明 | |------|------|------|------| | image | string | ✅ | 图片 URL、本地文件路径或 base64 data URI | | prompt | string | ❌ | 分析提示词,默认 请描述这张图片的内容 |

本地开发

git clone https://github.com/wly-wf/deep-vision.git
cd deep-vision
npm install
npm run build
npm start

开发模式(热重载):

npm run dev

License

MIT