mcp-image-recognition
If you are the rightful owner of mcp-image-recognition and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
An MCP server that provides image recognition capabilities using Anthropic and OpenAI vision APIs.
The MCP Image Recognition Server is a versatile tool designed to leverage the power of Anthropic and OpenAI vision APIs for image recognition tasks. It supports a variety of image formats including JPEG, PNG, GIF, and WebP, and offers configurable options for primary and fallback providers. The server can process images provided as Base64 data or as files, and it includes optional text extraction capabilities using Tesseract OCR. This makes it a robust solution for applications requiring detailed image descriptions and text extraction. The server is built to be flexible and can be configured to use different vision providers based on user preference, with support for both Anthropic and OpenAI models. It also integrates with OpenRouter to access a wider range of models using the OpenAI API format.
Features
- Image description using Anthropic Claude Vision or OpenAI GPT-4 Vision
- Support for multiple image formats (JPEG, PNG, GIF, WebP)
- Configurable primary and fallback providers
- Base64 and file-based image input support
- Optional text extraction using Tesseract OCR
Tools
describe_image
Input: Base64-encoded image data and MIME type. Output: Detailed description of the image.
describe_image_from_file
Input: Path to an image file. Output: Detailed description of the image.
