image-mcp
Click on "Deploy 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-mcp Analyze the image at /tmp/screenshot.png and return its content in XML"
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-mcp
基于 DashScope 视觉模型的本地 MCP server,用于识别本地或远程图片,并默认以 XML 形式返回图片内容,帮助 AI 理解图片。
安装
npm installRelated MCP server: image-mcp
MCP 配置
模型配置通过 MCP client 的 env 注入到 server 进程,不需要也不应该作为 tool 参数传递。
{
"mcpServers": {
"image-mcp": {
"command": "node",
"args": ["/absolute/path/to/image-mcp/src/index.mjs"],
"env": {
"DASHSCOPE_API_KEY": "your-api-key",
"VISION_MODEL": "qwen-vl-plus",
"DASHSCOPE_BASE_URL": "https://dashscope.aliyuncs.com/compatible-mode/v1"
}
}
}
}DASHSCOPE_BASE_URL 可省略,默认使用 https://dashscope.aliyuncs.com/compatible-mode/v1。
Tool
recognize_image
image_path: 本地图片路径,和image_url二选一。image_url: 远程图片 URL,和image_path二选一。prompt: 可选识图提示词,默认值为识别图像内容,使用xml形式输出,帮助ai理解图片内容。max_tokens: 可选最大输出 token 数,默认1024。
CLI
npm run vision -- ./dist/ScreenShot_2026-08-01_155219_072.png "识别图像内容,使用xml形式输出,帮助ai理解图片内容"
npm run vision -- --url https://example.com/image.png本地 npm 使用
如果只是本机使用,不需要发布到 npm registry。推荐用 npm link 或 npm pack。
方式一:npm link
在项目目录执行:
npm install
npm link然后 MCP 配置可以直接使用全局命令:
{
"mcpServers": {
"image-mcp": {
"command": "image-mcp",
"args": [],
"env": {
"DASHSCOPE_API_KEY": "your-api-key",
"VISION_MODEL": "qwen-vl-plus",
"DASHSCOPE_BASE_URL": "https://dashscope.aliyuncs.com/compatible-mode/v1"
}
}
}
}如果之后修改了源码,一般不需要重新 link;重启 MCP client 即可加载新代码。
取消本地链接:
npm unlink -g image-mcp方式二:npm pack
如果想模拟正式 npm 包安装,但仍然只在本地使用:
npm install
npm pack
npm install -g ./image-mcp-1.0.0.tgz安装后同样可以在 MCP 配置中使用:
{
"mcpServers": {
"image-mcp": {
"command": "image-mcp",
"args": [],
"env": {
"DASHSCOPE_API_KEY": "your-api-key",
"VISION_MODEL": "qwen-vl-plus"
}
}
}
}升级本地包时重新执行:
npm pack
npm install -g ./image-mcp-1.0.0.tgz检查命令
确认全局命令可用:
which image-mcp
image-mcpimage-mcp 是 MCP stdio server,直接运行后会等待 MCP client 输入;没有输出不代表失败。实际验证建议在 MCP client 中查看是否能列出 recognize_image 工具。
特殊说明
项目扩展自 : https://github.com/asuojun/claude-vision-skill/tree/master
Available Tools
1 toolrecognize_imageRecognize imageA
识别本地或远程图片内容,默认使用 XML 形式输出,帮助 AI 理解图片内容。
Inputs: prompt, image_url, image_path, max_tokens.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion between tools. The single recognize_image tool has a clear and distinct purpose.
The tool name recognize_image follows a clear verb_noun pattern, which is descriptive and predictable. With only one tool, the naming convention is inherently consistent.
Having a single tool feels thin for an image-related server. While the tool covers the core recognition function, the server lacks any additional utilities, making it borderline in scope.
The server's stated purpose is to help AI understand image content, and recognize_image fulfills this completely. There are no obvious missing operations within this narrow domain.
Maintenance
Related MCP Connectors
MCP server for Qwen Image 3 AI image generation
MCP server for ByteDance Seedream AI image generation
MCP server for Wan AI video generation
MCP server for Grok Imagine AI video generation
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server for analyzing images using ModelScope's vision models. Supports both local files and URLs, enabling image content description and question answering.1488 npm10MIT
- AlicenseAqualityDmaintenanceMCP server for image recognition, supporting multiple vision backends (Anthropic, Zhipu, Ollama) to describe, answer questions, and analyze images.355 npm1MIT
- FlicenseNot gradedqualityDmaintenanceMCP server that provides a 'borrowed eye' for text-only LLMs, enabling them to identify and describe local images via the Qwen VL vision model, including face recognition, scene description, OCR, and targeted visual questioning.-
- AlicenseAqualityDmaintenanceA local MCP server that gives vision to vision-less LLMs by describing images and extracting text via Alibaba DashScope vision models.2MIT