mcp-image-recognition
使用AI视觉API的图像识别服务器. mcp-image-recognition is a Model Context Protocol (MCP) server maintained by mario-andreschak. It connects to MCP-compatible clients such as Claude Desktop, Cursor, Cline, and other agents that speak the protocol. It exposes 2 tools, including describe_image and describe_image_from_file, that an agent can call directly. It is categorized under AI/Vision, Tool/Server and AI/OCR.
这是什么MCP
本MCP是一个图像识别服务器，利用Anthropic Claude Vision和OpenAI GPT-4 Vision API提供图像描述功能，并可选使用Tesseract进行OCR文本提取。
如何使用这个MCP
在.env文件中配置API密钥，然后使用Python或提供的批处理脚本运行服务器。向服务器端点发送图像数据（base64或文件路径）即可接收描述结果。
这个MCP的用途
用于自动生成图像描述以提升可访问性、内容分析、视觉数据处理，以及在文档处理或媒体分析等应用中从图像提取文本。
AIMCP authority
DR and traffic signal for the AIMCP public domain.
Frequently asked questions
What is the mcp-image-recognition MCP server?
mcp-image-recognition is a Model Context Protocol server from mario-andreschak. It lets MCP-compatible AI clients call its tools over a standard interface, so agents like Claude, Cursor, and Cline can use it without custom integration.
How do I connect mcp-image-recognition to my AI client?
Add mcp-image-recognition to your client's MCP configuration using the stdio or SSE connection shown in the usage examples on this page, then restart the client to load the server.
What tools does mcp-image-recognition provide?
mcp-image-recognition provides 2 tools: describe_image and describe_image_from_file.
Is mcp-image-recognition free to use?
mcp-image-recognition is listed on AIMCP for free. Any API keys or accounts required by the underlying service are set by its provider.
Vernclaw Plugins for OpenClaw
Ready-to-use connectors for SEO data, social reading & content generation. Pay-as-you-go credits with audit logs.