vision-mcp
The vision-mcp server provides visual analysis capabilities by exposing a single analyze_image tool that analyzes images using a vision-capable AI model.
You can:
Analyze local or remote images — provide a local file path or HTTP(S) URL
Ask custom questions about image content via an optional
prompt(e.g., "Read the text in this image", "What objects are shown?")Automatically handle large images — images exceeding 2048×2048 pixels are scaled down before processing
Use any OpenAI-compatible vision API — supports OpenAI, Azure, Ollama, vLLM, ModelScope, Zhipu GLM, and others via environment variables
Get detailed text descriptions of image content returned directly in the conversation
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., "@vision-mcpanalyze the image at https://example.com/photo.jpg"
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.
Vision MCP Server
Python 实现的 MCP (Model Context Protocol) 图片分析服务器 —— 为纯文本大模型提供视觉能力。
参考自 Markusbetter/vision-mcp-server（Node.js / TypeScript），在其基础上增加了大图自动缩放、多 API 提供商支持等功能。
功能特点
单一工具：
analyze_image— 分析图片内容并提供详细描述支持本地图片文件和远程 HTTP(S) URL
自动缩放：超过 2048×2048 像素的图片会自动等比缩放到长边 2047px 再发送，避免超大图直接报错
多提供商支持：兼容任意 OpenAI 兼容 API，通过环境变量切换——OpenAI、Azure、vLLM、Ollama、ModelScope 等均可
全部通过环境变量配置，无需配置文件
安装
uv（推荐）
# 克隆仓库
git clone https://github.com/Jian-1197/vision-mcp.git
cd vision-mcp
# 安装（editable 模式，修改源码即时生效）
uv tool install -e .安装完成后 vision-mcp 命令即全局可用。
需要 Python ≥ 3.10。
Conda
conda create -n mcp python=3.10 -y
conda activate mcp
pip install -e /path/to/vision-mcpvenv / pip
python -m venv .venv
source .venv/bin/activate # Linux/macOS
.venv\Scripts\activate # Windows
pip install -e /path/to/vision-mcp环境变量配置
变量 | 必填 | 说明 |
| ✅ | API 基础地址 |
| ✅ | API 密钥 |
| ✅ | 模型名 |
MCP 客户端配置
本服务通过 stdio 传输，运行命令为 vision-mcp。
以 Claude Desktop 为例：
{
"mcpServers": {
"vision": {
"command": "vision-mcp",
"env": {
"VISION_BASE_URL": "https://api.openai.com/v1",
"VISION_API_KEY": "sk-your-key-here",
"VISION_MODEL": "gpt-4o"
}
}
}
}若使用 Reasonix（1.x 配置文件路径为 ~\AppData\Roaming\reasonix\config.toml，可在软件中查看，或直接在 MCP 界面添加运行命令及环境变量）：
[[plugins]]
name = "vision"
type = "stdio"
command = "vision-mcp"
env = { VISION_BASE_URL = "https://api.openai.com/v1", VISION_API_KEY = "sk-your-key-here", VISION_MODEL = "gpt-4o" }免费服务示例
智谱 GLM-4.6V-Flash
智谱提供的免费视觉模型，128K 上下文，支持图片、视频、文件理解。文档
API Key 获取：访问 智谱开放平台 → 注册 → API Keys
{
"mcpServers": {
"vision": {
"command": "vision-mcp",
"env": {
"VISION_BASE_URL": "https://open.bigmodel.cn/api/paas/v4",
"VISION_API_KEY": "你的智谱APIKey",
"VISION_MODEL": "glm-4.6v-flash"
}
}
}
}魔搭社区 ModelScope
ModelScope 提供免费视觉模型调用额度，每日 2k 次。文档
API Token 获取：访问 ModelScope → 个人中心 → API 令牌
{
"mcpServers": {
"vision": {
"command": "vision-mcp",
"env": {
"VISION_BASE_URL": "https://api-inference.modelscope.cn/v1",
"VISION_API_KEY": "你的ModelScopeToken",
"VISION_MODEL": "Qwen/Qwen3-VL-30B-A3B-Instruct"
}
}
}
}工作原理
接收图片（本地路径 → 读取文件；URL → HTTP 下载）
若图片超过 2048px，用 Pillow 等比缩放
编码为 base64 data URI
发送到
{VISION_BASE_URL}/chat/completions（OpenAI 兼容格式）返回模型的文字描述
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.
Tools
Latest Blog Posts
- 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/Jian-1197/vision-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server