Moltline Vision Maths
Image header probing, bbox conversion, resize plans and colour maths. 4 of 6 free.
Connect it
Settings → Connectors → Add custom connector
URL: https://mcp.moltlinestudio.com/visionSettings → Apps & Connectors → Advanced → Developer mode
Create connector with URL: https://mcp.moltlinestudio.com/vision{
"mcpServers": {
"vision": {
"url": "https://mcp.moltlinestudio.com/vision"
}
}
}claude mcp add --transport http vision https://mcp.moltlinestudio.com/vision{
"servers": {
"vision": {
"type": "http",
"url": "https://mcp.moltlinestudio.com/vision"
}
}
}6 tools, verified live
image_proberead-onlyRead 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 {"format": "png", "width": 1920, "height": 1080, "aspect_ratio": 1.7778, "aspect_label": "16:9", "megapix
bbox_convertread-onlyConvert 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. Typical input {"boxes": [[10, 20, 100, 50]], "from_format": "coco", "to_format": "yolo", "image_width":
resize_planread-onlyWork 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, 360], "pad": {"left": 0, "top": 140, "right": 0, "bottom": 140}, "box_transform": "x_new = x * 0.3333
colour_checkread-onlyCheck 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, "required": {"AA": 4.5, "AAA": 7.0}, "verdict": "Passes AA for normal text, fails AAA."}. Use when gene
nmsread-onlyRemove 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. Typical input {"boxes": [[0,0,10,10],[1,1,11,11],[50,50,60,60]], "scores": [0.9, 0.8, 0.7]} returns {"kee
detection_metricsread-onlyScore 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-points interpolation used by Pascal VOC 2010 onward. Typical input {"predictions": [{"box": [0,0,10,
Alternatives in Design & Media
Compare →
TinyPNG MCP by usefulapiB
Compress, resize and convert images with TinyPNG by URL, and check this month's compression count.
APITemplate.io MCP by usefulapiB
Generate PDFs and images with APITemplate.io from templates, HTML, Markdown or a URL.
CraftMyPDF MCP by usefulapiB
Generate PDFs and images from CraftMyPDF templates; read templates, versions and usage.
Rev.ai MCP by usefulapiB
Transcribe audio with Rev.ai: submit jobs by URL, read transcripts, summaries and captions.
Speechmatics MCP by usefulapiB
Transcribe audio and video with Speechmatics speech-to-text from Claude and any MCP client.
Photon Health MCP by usefulapiB
Read Photon Health patients, prescriptions, orders, pharmacies and medications; screen interactions.