qwen-vision-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@qwen-vision-mcpAnalyze this image and describe what you see: /tmp/screenshot.png"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
Related MCP server: glm-vision-mcp-server
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
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables Claude Code to describe images and extract text using Kimi/Moonshot vision API. Supports local image files with customizable prompts.2MIT
- AlicenseAqualityCmaintenanceEnables Claude Code to analyze images using Zhipu AI's GLM-5V-Turbo vision model, supporting local files and URLs with customizable prompts.192MIT
- AlicenseAqualityCmaintenanceEnables to analyze local images or remote URLs using Alibaba Qwen3.7-plus vision model via DashScope's Anthropic-compatible endpoint.125MIT
- Flicense-qualityCmaintenanceEnables Claude Code to analyze images using multiple visual models (Kimi, OpenAI, etc.) and summarize results with DeepSeek. Supports dynamic switching of visual providers and handles both text and image inputs.1
Related MCP Connectors
Analyze images from multiple angles to extract detailed insights or quick summaries. Describe visu…
LLM chat, text summarization and AI image generation
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/hanasite/qwen-vision-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server