A
licenseNot graded
qualityD
maintenanceEnables AI agents to perform image processing tasks such as sprite sheet splitting, resizing, cropping, and batch operations on local images.
MIT
roundcut-mcp
by Araluma
Related Servers
Alternatives to roundcut-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to process images locally via file paths—converting, resizing, removing backgrounds, smart cropping, upscaling, reading or stripping metadata, and batch processing—without files ever leaving the device.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to locally process images with tools for cropping, zooming, enhancement, edge detection, segmentation, and text region extraction, all without external API keys. It uses PIL, OpenCV, and scikit-image for robust image analysis.MIT
- AlicenseNot gradedqualityCmaintenanceProvides AI agents with tools to convert images between formats and inspect image metadata, enabling seamless image processing within agent workflows.113MIT
- AlicenseNot gradedqualityAmaintenanceProvides local image understanding for text-only LLMs with tools for image analysis, OCR, object detection, and cropping, all processed on-device.2MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to perform GIMP-style image operations such as open, resize, crop, flip, rotate, blur, desaturate, text overlay, export, and batch processing via MCP tools, supporting both mock (Pillow) and live GIMP backends.1MIT
TDQS
A3.9/5.0
Scored across 7 tools
Disambiguation4/5
Each tool targets a distinct image operation, but compress_image and convert_image have some conceptual overlap since both involve re-encoding. The descriptions clarify that one keeps the format while the other changes it, so the ambiguity is mostly resolved. circle_crop is also distinct from crop_image because it adds a circular mask.
Naming Consistency4/5
Most tools follow a predictable verb_image pattern: compress_image, crop_image, resize_image, and convert_image. However, image_info is a noun phrase and roundcut_web_tools is a branded noun, which breaks the otherwise consistent convention.
Tool Count5/5
Seven tools is a well-scoped count for a local image-processing server: one inspection tool, five common transform tools, and one pointer to web-only features. No tool feels redundant, and the set is neither too thin nor bloated.
Completeness4/5
The tool surface covers core image workflows: inspect, compress, crop, circle-crop, resize, and convert. Minor gaps like rotate or flip are not covered, but the server explicitly points to web tools for advanced operations, so common local tasks do not hit dead ends.