# Moltline Vision Maths (remote · mcp.moltlinestudio.com)

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

- Trust score: 85/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `mcp.moltlinestudio.com`: 85/100 (this document), [markdown](https://verifymcp.io/servers/com-moltlinestudio-vision/vision.md), [page](https://verifymcp.io/servers/com-moltlinestudio-vision/vision)

## Channel facts

- Endpoint: `https://mcp.moltlinestudio.com/vision`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2380 tokens (~396/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "nms" implies "remove" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Moltline Vision Maths MCP server?

Moltline Vision Maths is a hosted endpoint at https://mcp.moltlinestudio.com/vision, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-moltlinestudio-vision 'https://mcp.moltlinestudio.com/vision'
```

### Cursor

```json
{
  "mcpServers": {
    "com-moltlinestudio-vision": {
      "url": "https://mcp.moltlinestudio.com/vision"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-moltlinestudio-vision": {
      "type": "http",
      "url": "https://mcp.moltlinestudio.com/vision"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-moltlinestudio-vision]
url = "https://mcp.moltlinestudio.com/vision"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-moltlinestudio-vision": {
      "type": "remote",
      "url": "https://mcp.moltlinestudio.com/vision",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-moltlinestudio-vision --url 'https://mcp.moltlinestudio.com/vision' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-moltlinestudio-vision:
    url: "https://mcp.moltlinestudio.com/vision"
```

### Netclaw

```json
{
  "McpServers": {
    "com-moltlinestudio-vision": {
      "Transport": "http",
      "Url": "https://mcp.moltlinestudio.com/vision"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-moltlinestudio-vision -t streamable-http -u 'https://mcp.moltlinestudio.com/vision'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-19 (score 85, +1)

- [security] Stability: 0.97 → pass

### 2026-09-17 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-06 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-04 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (6)

### `image_probe` (~309 tokens)

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 {"format": "png", "width": 1920, "height": 1080, "aspect_ratio":
1.7778, "aspect_label": "16:9", "megapixels": 2.07, "orientation":
"landscape", "bytes_inspected": 512}.

Use to find out what you are dealing with before planning a resize. Not for
pixel content - nothing here reads pixels - and not for EXIF. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "data_base64 must not be empty"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input parameters:

- `data_base64` (string, required): The image file, base64-encoded. The first few hundred bytes are enough for every supported format; send a prefix rather than a large file. Data-URL prefixes like "data:image/png;base64," are accepted…

### `bbox_convert` (~472 tokens)

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. Typical input {"boxes": [[10, 20, 100, 50]], "from_format":
"coco", "to_format": "yolo", "image_width": 640, "image_height": 480}
returns {"boxes": [[0.0938, 0.0938, 0.1562, 0.1042]], "converted": 1,
"rejected": []}.

Use whenever a dataset and a model disagree about format. Not for scoring
predictions (detection_metrics) and not for removing overlaps (nms). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "boxes must contain at least one box"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input parameters:

- `boxes` (array, required): Boxes to convert, each a list of exactly four numbers in from_format, e.g. [[10, 20, 100, 50]].
- `clip` (boolean): When true, clamp boxes to the image bounds instead of returning them as they are. Off by default, because a box outside the image is usually a bug worth seeing.
- `from_format` (string, required): "coco" for [x, y, w, h], "voc" for [x1, y1, x2, y2], or "yolo" for normalised [cx, cy, w, h].
- `image_height` (integer): Pixel height, required whenever yolo is on either side.
- `image_width` (integer): Pixel width, required whenever yolo is on either side.
- `to_format` (string, required): The format to convert to; same three choices.

### `resize_plan` (~417 tokens)

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, 360], "pad": {"left": 0, "top": 140, "right": 0,
"bottom": 140}, "box_transform": "x_new = x * 0.3333 + 0; y_new = y *
0.3333 + 140"}.

Use before feeding an image to a fixed-input model. Not for finding out the
image's size in the first place - that is image_probe. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "unknown target <value>; use one of <value> or set"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input parameters:

- `height` (integer, required): Source image height in pixels.
- `mode` (string): "letterbox" scales to fit and pads the remainder, preserving aspect; "cover" scales to fill and crops the overflow; "stretch" distorts to fit exactly. Default "letterbox".
- `target` (string): A named preset: "clip_224", "vit_384", "yolo_640", "sam_1024", "sd_512", "sd_768" or "detr_800". Ignored when target_size is set.
- `target_size` (integer): A square side length in pixels, overriding target. Use this for a size the presets do not cover.
- `width` (integer, required): Source image width in pixels.

### `colour_check` (~290 tokens)

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, "required": {"AA": 4.5, "AAA": 7.0}, "verdict": "Passes AA
for normal text, fails AAA."}.

Use when generating or auditing an interface. Not for converting colours
between spaces and not for palettes. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "foreground must be a hex colour like #767676"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input parameters:

- `background` (string, required): Background colour in the same notation.
- `foreground` (string, required): Text colour as hex, e.g. "#767676" or "767676" or "#777".
- `large_text` (boolean): True for text at least 18pt, or 14pt bold, which WCAG allows to pass at a lower ratio. Default false.

### `nms` (~391 tokens)

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. Typical input {"boxes": [[0,0,10,10],[1,1,11,11],[50,50,60,60]],
"scores": [0.9, 0.8, 0.7]} returns {"keep": [0, 2], "suppressed": [{"index":
1, "by": 0, "iou": 0.6807}], "kept": 2}.

Use after a detector that emits overlapping boxes. Not for scoring against
ground truth (detection_metrics) and not for format changes (bbox_convert). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "boxes and scores must be the same length"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input parameters:

- `box_format` (string): "voc", "coco" or "yolo". Default "voc".
- `boxes` (array, required): Candidate boxes in box_format, e.g. [[0, 0, 10, 10]].
- `image_height` (integer): Pixel height; required for yolo boxes.
- `image_width` (integer): Pixel width; required for yolo boxes.
- `iou_threshold` (number): Overlap above which the lower-scoring box is dropped. Default 0.5.
- `scores` (array, required): One confidence per box, same order and same length as boxes.

### `detection_metrics` (~447 tokens)

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-points interpolation used by Pascal VOC 2010 onward. Typical input
{"predictions": [{"box": [0,0,10,10], "label": "cat", "score": 0.9}],
"ground_truth": [{"box": [1,1,11,11], "label": "cat"}]} returns
{"overall": {"tp": 1, "fp": 0, "fn": 0, "precision": 1.0, "recall": 1.0,
"f1": 1.0}, "per_class": {...}, "mAP": 1.0}.

Use to compare two models on the same held-out set. Not for cleaning up a
single model's overlapping output first - run nms before this. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "ground_truth must contain at least one box"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input parameters:

- `box_format` (string): "voc", "coco" or "yolo". Default "voc".
- `ground_truth` (array, required): True boxes, each {"box": [...], "label": ...}.
- `image_height` (integer): Pixel height; required for yolo boxes.
- `image_width` (integer): Pixel width; required for yolo boxes.
- `iou_threshold` (number): Overlap at which a prediction counts as a match. Default 0.5, the usual reporting threshold.
- `predictions` (array, required): Predicted boxes, each {"box": [...], "label": ..., "score": ...}. Score defaults to 1.0 when omitted.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-moltlinestudio-vision/vision#diagnostics

## Score history

- 2026-09-21: 85
- 2026-09-20: 85
- 2026-09-19: 85
- 2026-09-18: 84
- 2026-09-17: 84
- 2026-09-16: 83
- 2026-09-15: 83
- 2026-09-14: 82
- 2026-09-13: 82
- 2026-09-12: 81
- 2026-09-11: 81
- 2026-09-10: 80
- 2026-09-09: 80
- 2026-09-08: 80
- 2026-09-07: 79
- 2026-09-06: 79
- 2026-09-05: 78
- 2026-09-04: 78
- 2026-09-03: 77
- 2026-09-02: 77
- 2026-09-01: 76
- 2026-08-31: 76
- 2026-08-30: 75
- 2026-08-29: 75
- 2026-08-28: 74
- 2026-08-27: 74
- 2026-08-26: 73
- 2026-08-25: 73
- 2026-08-24: 72
- 2026-08-23: 72

## Common questions

### What is the Moltline Vision Maths MCP server?

Moltline Vision Maths is an MCP server listed in the public MCP registry as com.moltlinestudio/vision. Image header probing, bbox conversion, resize plans and colour maths. 4 of 6 free. This page covers its hosted endpoint (https://mcp.moltlinestudio.com/vision).

### Is the Moltline Vision Maths MCP server safe to use?

Moltline Vision Maths scores 85 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Moltline Vision Maths MCP server expose?

Moltline Vision Maths exposes 6 tools: image_probe, bbox_convert, resize_plan, colour_check, nms, detection_metrics. Their descriptions and schemas cost roughly 2,326 tokens of context every time the server is loaded.

### Does the Moltline Vision Maths MCP server require authentication?

No. We connected to Moltline Vision Maths without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Moltline Vision Maths MCP server still maintained?

Moltline Vision Maths is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.moltlinestudio.com/vision
- Repository: https://github.com/GarphenGate/moltline-mcp
- Website: https://moltlinestudio.com/servers.html#vision
- Changelog RSS feed: https://verifymcp.io/servers/com-moltlinestudio-vision/vision.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-moltlinestudio-vision/vision.json
- HTML version of this page: https://verifymcp.io/servers/com-moltlinestudio-vision/vision