MCP Image Extractor is a server that enables AI models to process and analyze images by extracting them from URLs or base64-encoded data. It provides three main tools: extract_image_from_url for retrieving images from web sources, extract_image_from_base64 for processing already encoded images, and save_screenshot for storing images to disk. Built with TypeScript and using the Sharp library for image processing, it includes features like image resizing, format conversion, and domain filtering for security. The implementation can be deployed locally or via Docker, making it ideal for workflows where visual content analysis is needed within AI conversations.
Extracts an image from a local file and converts it to base64. Parameters: file_path (required): Path to the local image file.
Extracts an image from a URL and converts it to base64. Parameters: url (required): URL of the image to extract.
Processes a base64-encoded image for LLM analysis. Parameters: base64 (required): Base64-encoded image data; mime_type (optional, default: 'image/png'): MIME type of the image.
No reviews yet. Be the first to review!
Sign in to join the conversation
