mcp-image-recognition

What is this MCP

This MCP is an image recognition server that leverages Anthropic Claude Vision and OpenAI GPT-4 Vision APIs to provide image description capabilities, with optional OCR text extraction using Tesseract.

How to use this MCP

Configure API keys in the .env file, then run the server using Python or provided batch scripts. Send image data (base64 or file path) to the server's endpoints to receive descriptions.

What this MCP can be used for

Automated image description for accessibility, content analysis, visual data processing, and extracting text from images in applications like document processing or media analysis.