Servidor MCP

Image Tools - Background Removal, Upscaling & Face Restoration

io.github.fasuizu-br/image-tools
Diseño y creatividad Público y accesible MCP 2025-11-25

Qué hace este MCP

Processes images with GPU-accelerated background removal, super-resolution upscaling, and face restoration.

check_image_service
Check Image Service
Check health status of Image API services and loaded models. Returns: dict with keys: - status (str): 'healthy' or error state - models (dict): Loaded model status per capability - version (str): API version
Solo lectura Acceso externo Idempotente
Esquema de entrada
{'type': 'object', 'properties': {}}
remove_background
Remove Background
Remove the background from an image. Uses BiRefNet segmentation to precisely separate foreground from background. Returns a base64-encoded image with transparent background (PNG) or white background (WebP). Sub-500ms latency on GPU. Args: image_base64: Base64-encoded image data (PNG, JPEG, or WebP). output_format: Output format -- 'png' (with transparency) or 'webp'. Returns: dict with keys: - image_base64 (str): Base64-encoded result image - format (str): Output image format - original_size (dict): Original width and height - processing_ms (int): Processing time in milliseconds
Solo lectura Acceso externo Idempotente
Esquema de entrada
{'type': 'object', 'required': ['image_base64'], 'properties': {'image_base64': {'type': 'string', 'maxLength': 20000000, 'description': 'Base64-encoded image data. Supports PNG, JPEG, and WebP formats.'}, 'output_format': {'type': 'string', 'default': 'png', 'description': "Output image format: 'png' (default, with transparency) or 'webp'"}}}
restore_face
Restore Face
Restore and enhance faces in an image using GFPGAN. Detects all faces via RetinaFace, restores quality (fixes blur, noise, compression artifacts), and pastes them back. Optionally enhances the background using Real-ESRGAN. GPU-accelerated, sub-3s latency. Args: image_base64: Base64-encoded image data containing faces (PNG, JPEG, WebP). upscale: Output upscale factor -- 1 to 4 (default: 2). enhance_background: Whether to enhance background with Real-ESRGAN (default: true). Returns: dict with keys: - image (str): Base64-encoded restored image - format (str): Output image format - width (int): Output width - height (int): Output height - upscale (int): Scale factor applied - processing_time_ms (float): Processing time in milliseconds
Solo lectura Acceso externo Idempotente
Esquema de entrada
{'type': 'object', 'required': ['image_base64'], 'properties': {'upscale': {'type': 'integer', 'default': 2, 'description': 'Output upscale factor: 1-4 (default: 2)'}, 'image_base64': {'type': 'string', 'maxLength': 20000000, 'description': 'Base64-encoded image data containing one or more faces.'}, 'enhance_background': {'type': 'boolean', 'default': True, 'description': 'Enhance background with Real-ESRGAN (default: true)'}}}
upscale_image
Upscale Image
Upscale image resolution using Real-ESRGAN. Enhances image resolution by 2x or 4x using GPU-accelerated Real-ESRGAN super-resolution. Processes in tiles (256x256) to manage VRAM. Maximum output dimension: 8192x8192. Args: image_base64: Base64-encoded image data (PNG, JPEG, or WebP). scale: Upscale factor -- 2 or 4 (default: 4). Returns: dict with keys: - image (str): Base64-encoded upscaled image - format (str): Output image format - width (int): Output width - height (int): Output height - scale (int): Scale factor applied - processing_time_ms (float): Processing time in milliseconds
Solo lectura Acceso externo Idempotente
Esquema de entrada
{'type': 'object', 'required': ['image_base64'], 'properties': {'scale': {'type': 'integer', 'default': 4, 'description': 'Upscale factor: 2 or 4 (default: 4)'}, 'image_base64': {'type': 'string', 'maxLength': 20000000, 'description': 'Base64-encoded image data. Supports PNG, JPEG, and WebP formats.'}}}
Añadido
check_image_service
17 de September de 2026 a las 12:41
Añadido
restore_face
17 de September de 2026 a las 12:41
Añadido
upscale_image
17 de September de 2026 a las 12:41
Añadido
remove_background
17 de September de 2026 a las 12:41