zhipu-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., "@zhipu-vision-mcpExtract the error message from this screenshot"
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.
智谱视觉 MCP Server
🌐 为 DeepSeek 等纯文本模型提供视觉能力 —— 通过智谱免费视觉模型"看懂"图片。
原理
用户发图 → MCP 调用 GLM 视觉模型(免费)
→ 返回文字描述
→ DeepSeek / 任意文本模型基于描述推理Related MCP server: vision_mcp
快速开始
1. 获取 API Key
访问 智谱开放平台,登录后创建 API Key。
2. 安装
方式 A:npx 一键(推荐)
claude mcp add -s user zhipu-vision \
--env ZHIPU_API_KEY=你的密钥 \
-- npx github:apsuadwf/zhipu-vision-mcp方式 B:本地安装
git clone https://github.com/apsuadwf/zhipu-vision-mcp.git
cd zhipu-vision-mcp
npm install
npm link
claude mcp add -s user zhipu-vision --env ZHIPU_API_KEY=你的密钥 -- zhipu-vision-mcp4. 使用
直接在对话中提及图片,Claude 会自动调用视觉工具分析。也可以手动指定:
"帮我看看这张截图里的报错信息"
"分析这个 UI 设计有什么问题"
"提取这张表格图片里的数据"
可用工具
工具 | 功能 |
| 分析图片,返回详细文字描述 |
| OCR 提取图片中的文字 |
| 对比两张图片的差异 |
可用模型
模型 | 特点 |
| 最新免费模型,支持本地文件(Base64)和多图 |
| 带深度思考,分析更深入 |
| 首个免费模型,仅支持 URL 单图 |
高峰期可能遇到 429 限流,换另一个模型即可。
环境要求
Node.js >= 18
npm >= 9
项目结构
zhipu-vision-mcp/
├── index.mjs # MCP Server(单文件)
├── package.json # 依赖配置
└── README.md # 本文件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
- AlicenseBqualityDmaintenanceEnables vision capabilities for any AI model by routing image analysis requests through OpenRouter's vision models. It provides tools to analyze images from URLs, local file paths, or base64 data.Last updated29117MIT
- Flicense-qualityCmaintenanceEnables LLMs like DeepSeek to understand images by calling external vision models via OpenAI-compatible API. Provides tools to describe images or diagnose connectivity.Last updated
- AlicenseAqualityBmaintenanceBridges a vision model to enable text-only models like DeepSeek to describe images, extract text, and compare images via MCP tools.Last updated5678MIT
- AlicenseAqualityBmaintenanceBridges DeepSeek (text-only) with vision models via MCP, enabling image description and compression using any OpenAI-compatible visual API.Last updated3211MIT
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Analyze images from multiple angles to extract detailed insights or quick summaries. Describe visu…
Generate, edit and upscale AI video and images from any agent via VicSee.
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/apsuadwf/zhipu-vision-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server