images-handler
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., "@images-handler Describe the image I sent"
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.
images-handler
给只支持文本的模型(如 DeepSeek)补上"看图"能力的标准 MCP 服务。
DeepSeek 不能直接识别图片,但本服务通过 Cursor TypeScript SDK 在本机跑一个 Cursor agent(默认 composer-2,可换 Claude/GPT 视觉模型),把图片理解成文本描述返回。DeepSeek 调用工具拿到文字结果,就等于"能看图"了。
本服务只做图片识别:agent 始终以纯文本模式运行,不执行任何 shell/文件工具。
前置条件
Node.js ≥ 22.13
Cursor 凭据(二选一):
设置环境变量
CURSOR_API_KEY,或已用
Cursor.auth.login()登录过 Cursor 账号(SDK 自动读取存储的凭据)
Related MCP server: DeepSeek Eyes
安装与运行
npm install
npm start # 开发运行(stdio),等价 npx tsx src/index.ts
# 或构建后运行
npm run build && node dist/index.js环境变量
变量 | 默认 | 说明 |
| — | Cursor API key,缺省时回退登录态 |
|
| 视觉模型 id |
|
| 单次识别调用超时(毫秒) |
接入客户端
Claude Code
claude mcp add image-recognition -e CURSOR_API_KEY="${CURSOR_API_KEY}" -- npx tsx D:/path/to/images-handler/src/index.tsCursor
.cursor/mcp.json:
{
"mcpServers": {
"image-recognition": {
"command": "npx",
"args": ["tsx", "D:/path/to/images-handler/src/index.ts"],
"env": {
"CURSOR_API_KEY": "${CURSOR_API_KEY}"
}
}
}
}其他标准 MCP 客户端
stdio 传输,按标准协议配置启动命令即可(记得通过 env 传入 CURSOR_API_KEY)。
工具:recognize_image
参数 | 类型 | 必填 | 说明 |
| string 或 string[] | 是 | 图片 data URI( |
| string | 否 | 想针对图片问什么,缺省为"请详细描述这张图片的内容、画面元素和任何可见文字。" |
| string | 否 | 覆盖视觉模型(默认 |
示例
{
"images": ["data:image/png;base64,iVBORw0KGgo..."]
}带自定义指令:
{
"images": ["data:image/png;base64,iVBORw0KGgo..."],
"instruction": "识别图中的文字并翻译成中文"
}传本地文件路径(在服务所在机器上读取):
{
"images": ["D:/photos/screenshot.png"]
}说明与限制
每次工具调用都会新建一个独立 Cursor agent(调用间不共享会话历史),用完即关闭。
服务只做图片识别:agent 恒为纯文本模式(
tools: []),不执行 shell/文件工具,除传入的图片外不会读取或访问任何本地内容。传本地路径时,文件在服务所在机器上读取,并按扩展名识别为图片;非图片扩展名会被拒绝。请仅传入你自己信任的图片路径。
Available Tools
1 toolrecognize_imageA
Recognize and analyze the given image(s) with a vision model and return a text description. Use this to give text-only LLMs like DeepSeek image understanding.
Inputs: images (required), model, instruction.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion between tools. The single tool has a clear and distinct purpose.
The tool name 'recognize_image' follows a clear verb_noun convention. Although there are no other tools to compare, the naming is internally consistent and predictable.
The server has only 1 tool, which feels thin for an 'images-handler' name that implies a broader scope. However, the single tool is non-trivial and provides meaningful functionality, so it is borderline rather than severely inadequate.
The server only offers image recognition/analysis, missing any other image handling operations like editing, conversion, or resizing. Given the 'images-handler' naming, this is a significant gap that limits the server's usefulness for general image tasks.
Related MCP Connectors
MCP server for Qwen Image 3 AI image generation
MCP server for Flux AI image generation
Hosted Screenshots MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables any LLM to describe images from file paths, URLs, or base64 data by forwarding them to a supported vision provider such as OpenAI, Anthropic, or local Ollama models.378 npm10MIT
- AlicenseAqualityDmaintenanceAn MCP server that grants image recognition to text-only models like DeepSeek by forwarding images to vision models and returning text descriptions. Supports clipboard, pasted session images, and batch folder image recognition.53MIT
- AlicenseAqualityDmaintenanceA local MCP server that gives vision to vision-less LLMs by describing images and extracting text via Alibaba DashScope vision models.2MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that gives text-only LLMs like DeepSeek vision capabilities by converting images to text via vision APIs, enabling image description, OCR, and generation in MCP clients.1MIT