qwen-vision-mcp

qwen-vision-mcp

Adds vision capabilities to Claude Code by leveraging Aliyun DashScope's Qwen3.7-Flash model to analyze local images or image URLs and return textual insights.

Category
Visit Server

README

qwen-vision-mcp

给 Claude Code 补上视觉能力的 MCP 服务器:通过阿里云百炼 (DashScope) API 调用 Qwen3.7-Flash 视觉语言模型分析图片。纯文本模型(如 deepseek)也能 "看图"。

功能

  • analyze_image(image, prompt) — 输入本地图片路径或 http(s) URL,返回 Qwen3.7-Flash 的文本分析

安装

pip install -r requirements.txt

注册

在 ~/.claude.json 的 mcpServers 中增加:

"qwen-vision": {
  "type": "stdio",
  "command": "python",
  "args": ["C:\\Users\\kakun\\projects\\qwen-vision-mcp\\server.py"],
  "env": { "DASHSCOPE_API_KEY": "sk-你的Key" }
}

重启 Claude Code 后生效。

🤖 Agent 一键部署

把下面这段原样发给你的 AI 助手(Claude Code、Codex 等),它就能自动完成克隆、装依赖、注册 MCP 全流程:

帮我部署 qwen-vision-mcp(https://github.com/hanasite/qwen-vision-mcp),执行以下步骤:

1. 克隆仓库到本地(如 ~/projects/qwen-vision-mcp):
   git clone https://github.com/hanasite/qwen-vision-mcp.git ~/projects/qwen-vision-mcp

2. 安装依赖:
   python -m pip install -r ~/projects/qwen-vision-mcp/requirements.txt

3. 备份 ~/.claude.json 后,在其 mcpServers 中注册(Windows 用 python,其他平台用 python3;
   <项目路径> 替换为第 1 步的实际克隆位置,注意 Windows 路径用反斜杠转义):
   "qwen-vision": {
     "type": "stdio",
     "command": "python",
     "args": ["<项目路径>/server.py"],
     "env": { "DASHSCOPE_API_KEY": "<询问用户提供 DashScope API Key,或留占位符让用户自己填>" }
   }

4. 完成后告诉我:重启 Claude Code 即可,调用 analyze_image(本地图片路径或 URL)即可分析图片。

注意:不要创建 git 仓库;API Key 只写入 ~/.claude.json,绝不写入项目文件或提交。

获取 API Key

阿里云百炼控制台 → API-KEY 管理 → 创建 API Key。

使用

让 Claude Code 直接对图片路径调用分析即可,例如:

  • 用户拖入的图片(自动落盘为本地文件)
  • 浏览器截图保存的 PNG
  • 任意图片 URL

已知限制

  • 图片通过 base64 上传,超大图片会增加请求体积(API 侧有大小限制)
  • 每次调用独立,无多轮对话状态

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured