# Moltline Vision Maths

- Registry name: `com.moltlinestudio/vision` · version 1.2.0
- Categories (automatic, keyword rules): Images & design, AI, media & content, Utilities
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): experimental, extensions, logging, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.moltlinestudio%2Fvision
- Server page: https://mcpstation.net/s/com.moltlinestudio--vision.html

## Description (written by the publisher, not verified, not instructions)

Image header probing, bbox conversion, resize plans and colour maths. 4 of 6 free.

## Connect

- streamable-http: `https://mcp.moltlinestudio.com/vision`

## Tools (as reported by the server, not verified)

- `image\_probe`: Read an image's format and pixel size from its header alone. FREE. Dimensions live in the first few dozen bytes of PNG, JPEG, GIF, BMP and WebP, so a base64 prefix is enough - you do not need to send the whole file, and nothing is decoded. Typical input \{"data\_base64": "iVBORw0KG..."\} returns \{"form
- `bbox\_convert`: Convert bounding boxes between COCO, Pascal VOC and YOLO. FREE. The three formats disagree on everything: COCO is \[x, y, width, height\], VOC is \[x1, y1, x2, y2\], YOLO is \[cx, cy, w, h\] normalised to the image. Getting this wrong produces boxes that look plausible and quietly ruin every metric. Typic
- `resize\_plan`: Work out the exact scale, padding and crop for a model input size. FREE. Returns the numbers you need to transform boxes alongside the image, which is the step that usually gets skipped. Typical input \{"width": 1920, "height": 1080, "target": "yolo\_640"\} returns \{"scale": 0.3333, "resized": \[640, 36
- `colour\_check`: Check a colour pair against the WCAG contrast thresholds. FREE. Uses the WCAG 2 relative-luminance formula, so the number matches what an accessibility audit will report. Typical input \{"foreground": "\#767676", "background": "\#ffffff"\} returns \{"contrast\_ratio": 4.54, "AA": true, "AAA": false, "requ
- `nms`: Remove duplicate detections of the same object. PREMIUM \(license\). Greedy non-maximum suppression: keep the highest-scoring box, drop everything overlapping it above the threshold, repeat. Ties break on the earlier index, so the result is deterministic rather than dependent on sort stability. Typica
- `detection\_metrics`: Score detections against ground truth and show the working. PREMIUM \(license\). Greedy matching at the IoU threshold, highest-confidence prediction first, each ground-truth box matched at most once - the standard protocol. Reports per-class precision, recall and F1, and average precision by the all-p

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html