vision-mcp

vision-mcp

Enables LLMs to see clipboard screenshots without saving files, using free Grok visual models, and integrates seamlessly with Command Code, Cursor, Claude, and other coding agents.

Category
Visit Server

README

vision-mcp

纯文本模型看见图。复制截图即可,不用存文件、不用填网关。

默认视觉:Groq 免费 qwen/qwen3.6-27b

安装

cd D:\workplace\vision
python -m venv .venv
.venv\Scripts\pip install -e .
.venv\Scripts\python -m vision_mcp setup --key gsk_你的key

免费 key:https://console.groq.com/keys

setup 会:

  • 把 key 写到 %USERPROFILE%\.vision-mcp\config.json(不写进 mcp.json)
  • 自动接入本机已有的 Command Code / Grok / OpenCode / Cursor / Claude
  • 装上 vision-see skill

然后重启对应 agent,或 Command Code 里 /mcp 重连。

开关

.venv\Scripts\python -m vision_mcp disable
.venv\Scripts\python -m vision_mcp enable
.venv\Scripts\python -m vision_mcp status

不用时 disable。Command Code 也可在会话里 /mcp 断开,不必删配置。

用法

  1. 复制截图(Win+Shift+S
  2. 对 agent 说:看这张图 / 剪贴板报错是什么
  3. agent 调 vision_see,默认读剪贴板

[Image 1] 当剪贴板,不当路径。

工具

工具 作用
vision_see 看图。默认剪贴板,也吃 data URI / base64 / URL / 路径
vision_status 查配置和剪贴板有没有图

换模型

只在 %USERPROFILE%\.vision-mcp\config.json 里改,或设环境变量。不用动 MCP 配置。

{
  "api_key": "gsk_...",
  "model": "qwen-vl-max",
  "base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1"
}

手写配置

setup 已经写过就不用再贴。格式和 Command Code 一样:

{
  "mcpServers": {
    "vision": {
      "transport": "stdio",
      "enabled": true,
      "command": "D:\\workplace\\vision\\.venv\\Scripts\\python.exe",
      "args": ["-m", "vision_mcp"]
    }
  }
}

Key 不要写进这个文件。

贡献

欢迎 fork 后提 Pull Request。本仓库不开放 write 权限,别人不能直接 push。

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
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
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
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