Image-Vision MCP Server
Allows describing images using OpenAI's vision API, extracting textual descriptions from images.
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., "@Image-Vision MCP Serverdescribe the image located at /path/to/image.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.
Image-Vision MCP Server
让纯文本语言模型通过调用多模态 API 来"看懂"图片。
安装
pip install -r requirements.txtRelated MCP server: vision-mcp
配置
复制 .env.example 为 .env,填入 API Key:
IMAGE_OPENAI_API_KEY=sk-xxx
IMAGE_ANTHROPIC_API_KEY=sk-ant-xxx
IMAGE_PROVIDER=openai在 Claude Code 中使用
在项目根目录创建 .mcp.json:
{
"mcpServers": {
"image-vision": {
"command": "python",
"args": ["path/to/image-vision-mcp/server.py"],
"env": {
"IMAGE_OPENAI_API_KEY": "sk-xxx",
"IMAGE_PROVIDER": "openai"
}
}
}
}在 MiMo Code 中使用
在 MCP 设置面板中添加:
命令:
python参数:
你的路径/image-vision-mcp/server.py环境变量: 填入 API Key
使用
agent 会自动发现 describe_image 工具。用户发图后,agent 会调用它获取文字描述再回复。
也可以手动调用:
describe_image(image="path/to/photo.png", provider="openai")
describe_image(image="https://example.com/img.jpg", provider="anthropic")测试
# 测试 OpenAI
set IMAGE_OPENAI_API_KEY=sk-xxx && python test_image.py openai
# 测试 Anthropic
set IMAGE_ANTHROPIC_API_KEY=sk-ant-xxx && python test_image.py anthropicThis 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.
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/liunan-githu/image-vision-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server