Skip to main content
Glama

Vision MCP Server

截图 + 视觉模型分析 MCP 服务器,支持 Claude Code 等 MCP 客户端。

功能

工具

说明

describe_screen

截图并用视觉模型分析(支持全屏/主屏/指定窗口)

take_screenshot

纯截图保存,不分析

list_windows

列出当前所有可见窗口标题

describe_image

分析一张已有的图片文件

Related MCP server: Desktop MCP

安装

方式一:Claude Code 插件安装

claude /plugin install github.com/你的用户名/vision-mcp-server

方式二:手动配置

~/.mcp.json 中添加:

{
  "mcpServers": {
    "vision": {
      "command": "node",
      "args": ["路径/server.mjs"],
      "env": {
        "DASHSCOPE_API_KEY": "你的阿里云百炼 API Key"
      }
    }
  }
}

前置要求

  • Node.js ≥ 18

  • npm ≥ 9

  • 阿里云百炼 API Key:去 bailian.console.aliyun.com → API Key 创建

  • Windows:支持(PowerShell + .NET)

  • 可选Ollama + minicpm-v:8b(本地模型备用)

配置说明

环境变量

必填

默认值

说明

DASHSCOPE_API_KEY

-

阿里云百炼 API Key

VISION_CLOUD_MODEL

qwen-vl-plus

云端模型名

VISION_LOCAL_MODEL

minicpm-v:8b

本地备用模型

VISION_SCREENSHOT_DIR

~/Pictures/Screenshots

截图保存目录

用法示例

"帮我看看浏览器当前页面"
"截一张全屏截图"
"分析这张图片:C:\photo.jpg"
"现在有哪些窗口开着"
A
license - permissive license
-
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

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/leydidishc280-dotcom/vision-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server