image-understand-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-understand-mcp What's in this image? 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.
image-understand-mcp
让纯文本模型也拥有图片理解能力的 MCP 服务。
原理
纯文本大模型本身无法处理图片,但可以调用 MCP 工具。本服务作为一个 "视觉能力代理":
纯文本模型(Claude / GPT / 通义千问 等,无视觉能力)
│ 调用 MCP 工具 understand_image(image, prompt)
▼
image-understand-mcp(本服务)
│ 读取本地文件 / 下载 URL / 解析 base64 → data URI
│ 转发给你在配置中指定的视觉模型(OpenAI 兼容接口)
▼
视觉模型(GPT-4o / Qwen-VL / GLM-4V / Kimi-VL 等)
│ 返回图片的文字描述
▼
纯文本模型继续基于文字描述进行推理、回答你只需要在 MCP 配置里填一个"看得懂图"的模型的 API 信息,任何纯文本模型 接入这个 MCP 后,就能通过调用工具"看图说话"。
Related MCP server: image_mcp
功能
understand_image:分析一张图片,返回详细文字描述或针对指定问题的回答。image支持三种输入:本地文件路径、HTTP(S) URL、data URI / 裸 base64。prompt可选,自定义想让视觉模型回答的问题(如"提取图中所有文字")。provider可选,当配置了多个视觉模型时可指定使用哪一个。
list_vision_providers:列出当前配置的所有视觉模型及默认使用的模型。
安装
npm install
npm run build配置
所有配置通过环境变量传入(在 MCP 客户端的 env 字段中设置)。
方式一:单个视觉模型(最简单)
{
"mcpServers": {
"image-understand": {
"command": "node",
"args": ["/path/to/image-understand-mcp/dist/index.js"],
"env": {
"VISION_BASE_URL": "https://api.openai.com/v1",
"VISION_API_KEY": "sk-xxxxxxxx",
"VISION_MODEL": "gpt-4o"
}
}
}
}适用于任何 OpenAI 兼容协议的视觉模型服务,例如:
服务商 | VISION_BASE_URL 示例 | VISION_MODEL 示例 |
OpenAI |
|
|
阿里通义千问 |
|
|
智谱 AI |
|
|
月之暗面 Kimi |
|
|
硅基流动 SiliconFlow |
|
|
本地 Ollama |
|
|
方式二:配置多个视觉模型,供调用方按需选择
{
"mcpServers": {
"image-understand": {
"command": "node",
"args": ["/path/to/image-understand-mcp/dist/index.js"],
"env": {
"VISION_PROVIDERS": "[{\"name\":\"gpt4o\",\"baseUrl\":\"https://api.openai.com/v1\",\"apiKey\":\"sk-xxx\",\"model\":\"gpt-4o\"},{\"name\":\"qwen-vl\",\"baseUrl\":\"https://dashscope.aliyuncs.com/compatible-mode/v1\",\"apiKey\":\"sk-yyy\",\"model\":\"qwen-vl-plus\"}]",
"VISION_DEFAULT_PROVIDER": "gpt4o"
}
}
}
}配置后,纯文本模型调用 understand_image 时可传入 provider: "qwen-vl"
来指定使用哪个视觉模型;不指定则使用 VISION_DEFAULT_PROVIDER(缺省为
数组中的第一个)。
环境变量说明
变量 | 必填 | 说明 |
| 二选一 | 视觉模型 API 的 base URL(不含 |
| 二选一 | API Key |
| 二选一 | 模型名称 |
| 否 | 单次请求超时时间(毫秒),默认 60000 |
| 二选一 | JSON 数组,配置多个 provider(见上方示例) |
| 否 | 多 provider 时的默认 provider 名称 |
VISION_PROVIDERS 与 VISION_BASE_URL/VISION_API_KEY/VISION_MODEL 二选一;
若同时设置,优先使用 VISION_PROVIDERS。
本地开发
npm run dev # 用 tsx 直接运行 src/index.ts
npm run build # 编译到 dist/
npm run inspector # 用 MCP Inspector 交互式调试(需先 build)
node scripts/smoke-test.mjs # 端到端冒烟测试(mock 视觉模型 API,无需真实 API Key)常见问题
Q: 图片必须是什么格式?
A: 支持常见格式(PNG/JPEG/WebP/GIF/BMP),本地路径按扩展名或文件头判断类型,
URL 优先用响应头 Content-Type。
Q: 报错 "未找到视觉模型配置"?
A: 检查是否正确设置了 VISION_BASE_URL/VISION_API_KEY/VISION_MODEL,
或 VISION_PROVIDERS。
Q: 视觉模型返回错误? A: 工具会把视觉模型 API 返回的 HTTP 状态码和错误信息透传给调用方模型, 便于定位是 Key 无效、模型名不对,还是配额不足。
Available Tools
2 toolslist_vision_providers列出可用视觉模型A
列出当前 MCP 服务配置的所有视觉模型 provider 及其名称、模型标识,以及默认使用哪一个。
Inputs: no named parameters.
understand_image图片理解A
分析一张图片并返回详细的文字描述。用于让不具备视觉能力的纯文本模型间接'看懂'图片:传入本地文件路径、图片 URL 或 base64 编码数据,本工具会调用配置好的视觉模型完成识别,并返回自然语言描述文本。适合需要理解截图、照片、图表、文档扫描件等内容的场景。
Inputs: image (required), prompt, mimeType, provider.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: understand_image performs image analysis, while list_vision_providers only lists configured providers. There is no overlap in function or input, so an agent can easily select the correct tool.
Both names use snake_case and follow a verb_noun pattern: understand_image and list_vision_providers. The convention is consistent and predictable across the entire set.
With only 2 tools, the set is borderline thin; one is a core operation and the other is auxiliary. While it matches the narrow purpose, it falls below the typical 3–15 range for a well-scoped server.
The core operation of understanding images and a helper to list providers are present, covering the main workflow. A minor gap exists: understand_image uses the configured default model with no parameter to select a specific provider per call, despite list_vision_providers exposing options.
Maintenance
Related MCP Connectors
Image & PDF tools for AI agents: compress, convert, resize, PDF, AI vision, pipeline.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Video, audio, and image processing for AI agents: convert, transcribe, upscale - 150+ operations.
Image and video AI tools and your own pipelines, run from any AI assistant.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables image analysis and understanding using Vision Language Models through OpenAI-compatible APIs. Supports analyzing images from URLs or local files with custom prompts.12MIT
- AlicenseNot gradedqualityDmaintenanceEnables text-only LLMs to analyze images by routing them to an OpenAI-compatible vision backend, supporting local files, URLs, and data URLs.22 npmMIT
- AlicenseAqualityDmaintenanceEnables LLMs to analyze images via OpenAI-compatible multimodal models, supporting local files, base64, and URLs with safety validation and model selection.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables text-only LLMs to analyze, OCR, and compare images by forwarding them to vision-capable models via OpenAI or Anthropic APIs.34 npmMIT