Moltline Vision Maths

Last 30 days

Uptime

100%

Response time

170 ms typical, 170 ms slowest 5%

Last check

3 h ago

Next check

in 4 h

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "moltline-vision-maths": {
      "type": "http",
      "url": "https://mcp.moltlinestudio.com/vision"
    }
  }
}

6 tools

• 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": "iVBORw0K

• 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 rui

• 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

• 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

• 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 s

• 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 p

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks