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-mcp识别截图 D:\screenshots\ui.png 中的按钮和坐标"
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(或任何支持 MCP 的客户端)挂上 Qwen3-VL 视觉能力的 MCP 服务器。 让纯文本主模型也能 OCR、识别截图 / UI 元素、理解图表。
后端走阿里云百炼(DashScope)的 OpenAI 兼容接口,默认模型 qwen3-vl-235b-a22b-thinking。
功能
工具 | 说明 |
| 分析单张本地图片(OCR / UI 识别 / 图表理解) |
| 并行分析多张图片 |
内置 缓存:同一张图 + 同一问题第二次直接秒回(不重复调用 API)。
fast=True 时关闭 thinking(enable_thinking: false):小图/简单任务实测约快 2.4x;
大图收益很小(瓶颈在视觉 token 处理),可保持默认。
Related MCP server: Luma MCP
安装
需要 Python 3.10+。
cd qwen-vision-mcp
python -m venv .venv
.venv/Scripts/python.exe -m pip install -r requirements.txt # Windows
# .venv/bin/python -m pip install -r requirements.txt # macOS / Linux⚠️
requirements.txt锁定mcp>=1.2.0,<2。不要装 mcp 2.x —— 它移除了FastMCP,API 完全不兼容。
配置
cp .env.example .env编辑 .env 填入你的阿里云百炼 API Key 和模型名。.env 已被 .gitignore 排除,不会提交。
注册到 Claude Code
claude mcp add --scope user --transport stdio qwen-vision -- \
"C:/path/to/qwen-vision-mcp/.venv/Scripts/python.exe" \
"C:/path/to/qwen-vision-mcp/server.py"然后 重启 Claude Code(MCP 服务器只在启动时加载)。
用法示例
在 Claude Code 会话里直接说:
用 analyze_image 看看
D:\screenshots\ui.png,识别里面的按钮和坐标
用 fast 模式批量分析
imgs/下的截图,提取每张的文字
提取这张网页截图里的新闻标题
安全提示
API Key 只存在本地
.env,不要提交到任何仓库。若 Key 疑似泄露,去百炼控制台吊销重发。
涉及精确信息(价格、数字、坐标)时,请在 prompt 里强调"只按图中可见内容回答,不要推测"。
项目结构
server.py # MCP 服务器(FastMCP + DashScope OpenAI 兼容接口)
test.py # 端到端测试(自生成测试图 → 调用分析)
smoke_stdio.py # MCP stdio 协议冒烟测试
bench.py # 并行 vs 串行基准测试
requirements.txt
.env.example
docs/setup-notes.md # 搭建过程、踩坑与性能实测License
MIT
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
- AlicenseBqualityDmaintenanceA local vision-language MCP server that enables Claude Code to perform image analysis, OCR, and UI-to-code generation using the Qwen3 VL 4B model via LM Studio. It provides privacy-focused visual processing by running entirely on the user's local hardware without external API dependencies.Last updated3381MIT
- AlicenseAqualityAmaintenanceMulti-model vision understanding MCP server that provides unified image analysis for AI assistants without native vision, supporting models like GLM-4.6V, DeepSeek-OCR, Qwen3-VL-Flash, and more.Last updated11,64982MIT
- AlicenseAqualityBmaintenanceMCP server for vision AI — screenshots to code, OCR, error diagnosis, and image analysis via OpenAI-compatible APIs.Last updated82MIT
- AlicenseAqualityCmaintenanceA universal vision MCP server that enables Claude Code and Claude Desktop to describe images, extract text, and answer questions about images by converting visual content to text via multiple AI providers.Last updated310MIT
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
MCP server for AI dialogue using various LLM models via AceDataCloud
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/Bigcheese18/qwen-vision-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server