Image Tools - Background Removal, Upscaling & Face Restoration is an MCP server published by io.github.fasuizu-br, hosted at apim-ai-apis.azure-api.net. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 4 tools, including remove_background, upscale_image, restore_face, check_image_service.
Background removal, 4x upscaling, and face restoration via GPU
14 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
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
| Parameter | Type | Description |
|---|---|---|
| image_base64 * | string | Base64-encoded image data. Supports PNG, JPEG, and WebP formats. |
| output_format | string | Output image format: 'png' (default, with transparency) or 'webp' |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
{
"name": "remove_background",
"title": "Remove Background",
"description": "Remove the background from an image.\n\nUses BiRefNet segmentation to precisely separate foreground from background.\nReturns a base64-encoded image with transparent background (PNG) or white\nbackground (WebP). Sub-500ms latency on GPU.\n\nArgs:\n image_base64: Base64-encoded image data (PNG, JPEG, or WebP).\n output_format: Output format -- 'png' (with transparency) or 'webp'.\n\nReturns:\n dict with keys:\n - image_base64 (str): Base64-encoded result image\n - format (str): Output image format\n - original_size (dict): Original width and height\n - processing_ms (int): Processing time in milliseconds",
"inputSchema": {
"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'"
}
}
},
"annotations": {
"title": "Remove Background",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}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
| Parameter | Type | Description |
|---|---|---|
| scale | integer | Upscale factor: 2 or 4 (default: 4) |
| image_base64 * | string | Base64-encoded image data. Supports PNG, JPEG, and WebP formats. |
{
"name": "upscale_image",
"title": "Upscale Image",
"description": "Upscale image resolution using Real-ESRGAN.\n\nEnhances image resolution by 2x or 4x using GPU-accelerated Real-ESRGAN\nsuper-resolution. Processes in tiles (256x256) to manage VRAM.\nMaximum output dimension: 8192x8192.\n\nArgs:\n image_base64: Base64-encoded image data (PNG, JPEG, or WebP).\n scale: Upscale factor -- 2 or 4 (default: 4).\n\nReturns:\n dict with keys:\n - image (str): Base64-encoded upscaled image\n - format (str): Output image format\n - width (int): Output width\n - height (int): Output height\n - scale (int): Scale factor applied\n - processing_time_ms (float): Processing time in milliseconds",
"inputSchema": {
"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."
}
}
},
"annotations": {
"title": "Upscale Image",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}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
| Parameter | Type | Description |
|---|---|---|
| upscale | integer | Output upscale factor: 1-4 (default: 2) |
| image_base64 * | string | Base64-encoded image data containing one or more faces. |
| enhance_background | boolean | Enhance background with Real-ESRGAN (default: true) |
{
"name": "restore_face",
"title": "Restore Face",
"description": "Restore and enhance faces in an image using GFPGAN.\n\nDetects all faces via RetinaFace, restores quality (fixes blur, noise,\ncompression artifacts), and pastes them back. Optionally enhances the\nbackground using Real-ESRGAN. GPU-accelerated, sub-3s latency.\n\nArgs:\n image_base64: Base64-encoded image data containing faces (PNG, JPEG, WebP).\n upscale: Output upscale factor -- 1 to 4 (default: 2).\n enhance_background: Whether to enhance background with Real-ESRGAN (default: true).\n\nReturns:\n dict with keys:\n - image (str): Base64-encoded restored image\n - format (str): Output image format\n - width (int): Output width\n - height (int): Output height\n - upscale (int): Scale factor applied\n - processing_time_ms (float): Processing time in milliseconds",
"inputSchema": {
"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)"
}
}
},
"annotations": {
"title": "Restore Face",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}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
No parameters.
{
"name": "check_image_service",
"title": "Check Image Service",
"description": "Check health status of Image API services and loaded models.\n\nReturns:\n dict with keys:\n - status (str): 'healthy' or error state\n - models (dict): Loaded model status per capability\n - version (str): API version",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"title": "Check Image Service",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Image Processing API suite with 3 capabilities: 1. **Background Removal** -- remove_background removes the background from images. 2. **Image Upscaling** -- upscale_image enhances image resolution using Real-ESRGAN (2x-4x). 3. **Face Restoration** -- restore_face restores and enhances faces using GFPGAN. All tools accept/return base64-encoded images.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.