Claude MarketplacesSubmit
fasuizu-br avatar

Image Tools - Background Removal, Upscaling & Face Restoration

fasuizu-br/speech-ai-examples

GPU-accelerated image processing over HTTP. Exposes three operations: background removal with BiRefNet, 4x upscaling via ESRGAN, and face restoration using GFPGAN. All endpoints accept base64-encoded images and run on Azure A10 GPUs with sub-3-second latency. Part of Brainiall's production API suite, so you get the same models whether you're using the MCP tools in Claude Desktop or hitting the REST endpoints directly. Costs $0.003-0.005 per image. Reach for this when you need agent-driven image cleanup without spinning up your own inference infrastructure or managing model downloads.

tools
4
transport
HTTP
last updated
Mar 5, 2026
View on GitHub

Install

From registry metadata
$ npx add-mcp https://apim-ai-apis.azure-api.net/mcp/image/mcp --name image-tools

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http image-tools https://apim-ai-apis.azure-api.net/mcp/image/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 4 tools

Verified live against the running server on Nov 6, 2026.

remove_backgroundRemove 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 dat...2 params

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 dat...

Parameters* required
image_base64*string
Base64-encoded image data. Supports PNG, JPEG, and WebP formats.
output_formatstring
Output image format: 'png' (default, with transparency) or 'webp'default: png
upscale_imageUpscale 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...2 params

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...

Parameters* required
image_base64*string
Base64-encoded image data. Supports PNG, JPEG, and WebP formats.
scaleinteger
Upscale factor: 2 or 4 (default: 4)default: 4
restore_faceRestore 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: B...3 params

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: B...

Parameters* required
enhance_backgroundboolean
Enhance background with Real-ESRGAN (default: true)default: true
image_base64*string
Base64-encoded image data containing one or more faces.
upscaleinteger
Output upscale factor: 1-4 (default: 2)default: 2
check_image_serviceCheck 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

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. Call it with no arguments.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

Details

Repository
github.com/fasuizu-br/speech-ai-examples
Website
brainiall.com
Category
Media & Entertainment
Transport
HTTP
Registry
MCP registry, active
Tools verified
Nov 6, 2026

More from fasuizu-br

Related Media & Entertainment MCP servers

View all
1fasuizu-br avatarNLP Tools - Sentiment, NER, Toxicity & Language Detectionfasuizu-br/speech-ai-examplesToxicity, sentiment, NER, PII detection, and language identification tools0stars
2scrape-badger avatarScrapeBadgerscrape-badger/scrapebadger-mcpTwitter/X, Google, Facebook Marketplace, Yelp, GitHub and AutoScout24 for AI agents.2stars
3helbertparanhos avatarPost for Me MCP Prohelbertparanhos/postforme-mcp-proPublish, schedule and analyze social posts across 9 platforms via the Post for Me API.1stars
4acedatacloud avatarMcp Klingacedatacloud/klingmcpMCP server for Kling AI video generation1stars
5realcrabcut avatarCrabcutrealcrabcut/crabcut-mcp-serverTurn YouTube videos into short-form clips from any AI assistant1stars
6starsinger-ai avatarStarsinger Mcpstarsinger-ai/starsinger-mcpMCP server for StarSinger AI music catalog — search, stream & browse AI-generated tracks1stars