ai-vision
Provides image analysis capabilities through OpenAI-compatible vision models, including analyzing local images (path or base64), remote image URLs, multi-image comparison, and listing available models.
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., "@ai-vision Analyze the image at https://example.com/cat.jpg and describe what you see."
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.
ai-vision
支持 OpenAI 兼容协议的视觉识别 MCP 服务器。让 Claude Desktop / Cline / Cherry Studio 等 MCP 客户端获得图片识别能力,可接入 OpenAI、通义千问、智谱、Moonshot 等任意 OpenAI 兼容服务商。
📖 完整使用说明(中文): docs/使用说明.html
快速开始
pnpm install
pnpm build
# 方式一:环境变量(也可直接在 MCP 客户端的 env 字段里注入)
OPENAI_API_KEY=sk-xxx node dist/index.js
# 方式二:配置文件(支持多服务商,参考 sample-config.json)
cp sample-config.json config.json
node dist/index.js --config=config.jsonRelated MCP server: vision-mcp
MCP 客户端配置(推荐:env 注入,无需配置文件)
{
"mcpServers": {
"vision": {
"command": "ai-vision",
"args": [],
"env": {
"OPENAI_API_KEY": "sk-你的密钥",
"OPENAI_BASE_URL": "https://api.openai.com/v1",
"OPENAI_MODEL": "gpt-4o"
}
}
}
}提供的 MCP 工具
工具 | 功能 |
| 分析本地图片(路径 / base64) |
| 分析远程图片 URL |
| 多图对比(最多 10 张) |
| 查询服务商可用模型 |
技术栈
@modelcontextprotocol/sdk — MCP 服务器框架(stdio / Streamable HTTP)
openai — OpenAI 兼容协议客户端
TypeScript + pnpm
测试
pnpm test # 本地 mock 服务器验证协议格式,无需真实 API KeyAvailable Tools
4 toolsanalyze_imageA
分析一张本地图片(通过路径或 base64 数据传入),返回视觉模型的识别结果
Inputs: model, prompt, provider, mime_type, +4 more.
analyze_imagesA
同时分析多张图片(路径/base64/URL 混合),用于对比、找差异、多图综合理解
Inputs: images (required), model, prompt, provider, +2 more.
analyze_image_urlB
分析一张远程图片(通过 http/https URL 传入),返回视觉模型的识别结果
Inputs: url (required), model, prompt, provider, +2 more.
list_modelsA
查询当前服务商支持的模型列表(调用 /v1/models)
Inputs: provider.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool targets a distinct input type (local image, remote image, multiple images, models). No overlap between analyze tools is present.
All tools follow a clear verb_noun pattern: list_models and analyze_* are consistent and predictable.
Four tools is well-scoped for a vision analysis server, covering model listing and image analysis without unnecessary bloat.
The set covers the core workflows: listing available models, analyzing local and remote images, and multi-image analysis. No obvious gaps for the domain.
Maintenance
Related MCP Connectors
Generate AI images and videos from any compatible MCP client.
Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
MCP server exposing the YourImageShare upload API (upload/list/delete) as tools for AI agents.
Related MCP Servers
- AlicenseAqualityCmaintenanceGive MCP-compatible AI agents image analysis, metadata inspection, cropping, OCR, and image comparison through any OpenAI-compatible vision model.6MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for analyzing images using multiple vision LLM providers (OpenCode, OpenAI, Anthropic, Google, and custom OpenAI-compatible endpoints). Provides tools to analyze single or multiple images, list providers, and test vision capabilities.MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server for image recognition and OCR via OpenAI-compatible vision APIs, supporting local files, URLs, and data URLs. Enables natural language image description and text extraction.2MIT
- AlicenseNot gradedqualityCmaintenanceEnables image analysis via OpenAI-compatible vision APIs, supporting local files, URLs, and base64 inputs with intelligent tiling for high-resolution images. Provides a secure, configurable MCP stdio server for structured vision analysis.91 npm3MIT