deepseek-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., "@deepseek-vision-mcpAnalyze this image and describe what's in it: /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.
deepseek-vision-mcp
让纯文本大语言模型 Agent(如 DeepSeek 系)获得「眼睛」的 MCP 项目:通过标准 MCP 工具调用智谱 GLM-4.6V-Flash(免费视觉模型),完成图片 / 视频 / 文件三种模态的理解,并以纯文本结果回传给 Agent。
底层模型:智谱 GLM-4.6V-Flash(免费,128K 上下文,支持思考模式) 官方文档:https://docs.bigmodel.cn/cn/guide/models/free/glm-4.6v-flash
架构:MCP 执行层 + Skill 决策层
┌─────────────────────────────────────────────────────┐
│ 文本模型 Agent(DeepSeek 等)—— 只懂文字 │
│ · 读取 Skill 的业务规则,决定何时调用什么工具 │
└──────────────────────┬──────────────────────────────┘
│ MCP 协议(stdio)
┌──────────────────────▼──────────────────────────────┐
│ MCP Server(本仓库,Python)—— 真实执行 │
│ · 读本地文件 / 图片 → base64 编码 │
│ · 调用智谱 API(认证、重试、超时、异常分类) │
│ · 提供标准化工具:vision_analyze_image / _video / _file │
└──────────────────────┬──────────────────────────────┘
│ HTTPS
┌──────────────────────▼──────────────────────────────┐
│ 智谱 GLM-4.6V-Flash API(视觉理解,返回文本) │
└─────────────────────────────────────────────────────┘职责分离:
层 | 职责 | 位置 |
MCP | 真实执行:读文件、base64、调 API、重试、异常捕获、统一错误结构 |
|
Skill | 业务规则:何时调用、传什么参数、输出格式、降级策略 |
|
Related MCP server: glm-vision-mcp
功能
图片理解:本地图片路径(自动 base64)或公网 URL
视频理解:公网视频 URL(本地视频需先提供可访问 URL)
文件理解:PDF / 文本等文档(公网 URL;本地文件需先提供可访问 URL)
思考模式:可选开启(
thinking=true),适合需要深度推理的视觉任务健壮性:3 次指数退避重试(429 / 5xx / 超时)、60s 超时、结构化错误返回(不抛未处理异常)
从 Release 安装(推荐给其他用户)
项目发布在 GitHub Releases,包含可直接安装的构建产物(wheel / sdist 源码包), 无需克隆仓库:
# 方式 A:直接 pip 安装 Release 的 wheel(最简单)
pip install "deepseek-vision-mcp @ https://github.com/JunHua-ECJTU/deepseek-vision-mcp/releases/latest/download/deepseek_vision_mcp-0.1.0-py3-none-any.whl"
# 方式 B:下载 wheel 后本地安装
pip install deepseek_vision_mcp-0.1.0-py3-none-any.whl
# 方式 C:源码包(sdist,含 skills/ 目录与测试)
pip install deepseek_vision_mcp-0.1.0.tar.gz国内网络安装依赖可加镜像:-i https://pypi.tuna.tsinghua.edu.cn/simple
详细的多 agent 部署步骤(Claude Code / Cursor / Cline / Reasonix / Claude Desktop 等 的 MCP 注册模板、Skill 安装、验证方法)见 docs/DEPLOY.md。
快速开始
1. 安装依赖
# Python ≥ 3.10
pip install -e ".[dev]"
# 国内网络可加镜像:-i https://pypi.tuna.tsinghua.edu.cn/simple2. 配置 API Key
cp .env.example .env
# 编辑 .env,填入你的智谱 API Key(https://bigmodel.cn/usercenter/proj-mgmt/apikeys)3. 启动 MCP Server
deepseek-vision-mcp
# 或:python -m deepseek_vision_mcp.server4. 配置到你的 Agent(MCP 客户端)
以支持 stdio MCP 的客户端为例,注册一个 MCP server:
{
"mcpServers": {
"deepseek-vision": {
"command": "python",
"args": ["-m", "deepseek_vision_mcp.server"],
"env": { "ZHIPU_API_KEY": "你的Key(或从环境变量注入)" }
}
}
}5. 安装 Skill(业务规则层)
将 skills/vision-agent/ 安装到你的 Agent 的 skills 目录,Agent 即会遵循其中的业务规则(何时调用工具、参数规范、输出格式、降级策略)。
MCP 工具
工具 | 说明 | 关键参数 |
| 图片理解(本地路径或 URL) |
|
| 视频理解(URL) |
|
| 文件理解(URL,PDF/文本等) |
|
所有工具返回统一结构:
{
"ok": true,
"content": "模型的文本回答",
"thinking": "思考内容(如开启)",
"usage": { "prompt_tokens": 123, "completion_tokens": 45 }
}失败时返回 {"ok": false, "error": {"code": "...", "message": "..."}},错误码包括 FILE_NOT_FOUND、UNSUPPORTED_FORMAT、AUTH_ERROR、API_ERROR、TIMEOUT、MODALITY_NOT_SUPPORTED 等。
注意事项
GLM-4.6V-Flash 不支持同时理解多种模态(图片/视频/文件一次只传一种)——Skill 层已约束
视频/文件模态要求可访问的 URL(本地路径需先上传到可访问位置)
.env已加入.gitignore,API Key 永不入库
测试
pytest许可证
MIT
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
- 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.13,03998MIT
- Flicense-qualityCmaintenanceAn MCP server that leverages Zhipu's free GLM-4.6V-Flash vision model to enable image, video, and file understanding (OCR, table parsing, defect detection, document Q&A, and more) across MCP-compatible clients like Codex and Claude Desktop.
- Flicense-qualityCmaintenanceMCP server that gives text-only models vision capabilities via free GLM vision models, supporting image description, OCR, chart/document analysis, and grounding with automatic model fallback.1
- Flicense-qualityCmaintenanceA Model Context Protocol server that wraps the free GLM-4.6V-Flash vision model, enabling text-only LLM clients like Codex, Cursor, and Claude Desktop to analyze images, videos, and files (PDF/TXT) through standard MCP tools.2
Related MCP Connectors
MCP server for AI dialogue using various LLM models via AceDataCloud
MCP server for GLM chat completions using Zhipu AI models via AceDataCloud
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/JunHua-ECJTU/deepseek-vision-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server