# three.ws Vision (npm · @three-ws/vision-mcp)

Image understanding for AI agents — analyze and describe any image via the three.ws pipeline.

- Trust score: 66/100 (medium)
- Change this week: +24
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- npm · `@three-ws/vision-mcp`: 66/100 (this document), [markdown](https://verifymcp.io/servers/nirholas-vision-mcp/three-ws-vision-mcp.md), [page](https://verifymcp.io/servers/nirholas-vision-mcp/three-ws-vision-mcp)

## Channel facts

- Registry: `npm`
- Package: `@three-ws/vision-mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-08-04.

- **Supply Chain Security**: 83/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known medium-severity CVE affects hono 4.12.33, reached via @modelcontextprotocol/sdk > hono. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 30 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 914 tokens (~304/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add nirholas-vision-mcp -- npx -y @three-ws/vision-mcp
```

### Codex

```bash
codex mcp add nirholas-vision-mcp -- npx -y @three-ws/vision-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nirholas-vision-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@three-ws/vision-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add nirholas-vision-mcp --command npx --arg -y --arg @three-ws/vision-mcp
```

### Hermes

```yaml
mcp_servers:
  nirholas-vision-mcp:
    command: "npx"
    args: ["-y", "@three-ws/vision-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "nirholas-vision-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@three-ws/vision-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-04 (score 66, +3)

- [security regression] CVE-2026-69207 affects this package: medium
- [security regression] Known CVEs: partial → fail
- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 63, +45)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: Apache-2.0

### 2026-08-01 (score 18, +13)

- [functional improvement] Tool coverage: unverified → 100

### 2026-07-31 (score 5, −19)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 24, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 42)

First indexed and scored.

## MCP tools (3)

### `analyze_image` (~321 tokens)

Analyze an image against a prompt

Let the agent SEE an image and answer a question about it. Supply the image as `imageUrl` (a public https URL the vision server fetches) OR `image` (raw base64 / a data: URI), and a `prompt` describing what to extract — e.g. "What objects are in this scene?", "Read the text in this screenshot", "Is this avatar render rigged correctly?". Returns the model's answer as `text`, plus the `provider` and `model` that served it (a free NVIDIA NIM lane when available, an automatic paid backstop otherwise — the caller never pays). Analysis only: it does not store or mutate anything. Accepts JPEG, PNG, WebP, or GIF up to 12 MB; base64 inputs are size-checked before upload.

Input parameters:

- `image` (string): The image as raw base64 or a `data:image/...;base64,...` URI. Provide this OR `imageUrl`, not both.
- `imageType` (string): MIME type of a raw base64 `image` (ignored for data URIs / `imageUrl`). Defaults to image/jpeg.
- `imageUrl` (string): Public https URL of the image to analyze. Provide this OR `image`, not both.
- `maxTokens` (integer): Maximum tokens in the answer (16–2048). Higher = longer, more detailed reads. Default 512.
- `prompt` (string, required): The question or instruction about the image (what to extract, read, classify, or critique).

### `describe_image` (~313 tokens)

Describe an image in natural language

Get a plain-language description of an image — ideal for alt text, captions, or a quick "what is this?" read when you have no specific question. Supply the image as `imageUrl` (a public https URL) OR `image` (raw base64 / data: URI). Use `detail` to pick brief / standard / detailed, and `focus` to steer the description toward something specific (e.g. "the clothing", "any visible text"). Returns the prose as `description`, plus the `provider` and `model` that served it (free NVIDIA NIM first, automatic paid backstop otherwise — the caller never pays). Read-only; accepts JPEG, PNG, WebP, or GIF up to 12 MB.

Input parameters:

- `detail` (string): How much description to return: brief (one sentence), standard (2–3 sentences), or detailed (a full paragraph).
- `focus` (string): Optional aspect to emphasize in the description (e.g. "any visible text", "the background", "the pose").
- `image` (string): The image as raw base64 or a `data:image/...;base64,...` URI. Provide this OR `imageUrl`, not both.
- `imageType` (string): MIME type of a raw base64 `image` (ignored for data URIs / `imageUrl`). Defaults to image/jpeg.
- `imageUrl` (string): Public https URL of the image to describe. Provide this OR `image`, not both.

### `get_vision_status` (~106 tokens)

Vision availability + accepted formats

Check whether the three.ws vision pipeline is live on the target deployment and which image formats it accepts. Returns `configured` (true when at least one VLM provider — a free NVIDIA NIM lane or the paid backstop — can serve a request) and `image_types` (the accepted MIME types). Use this before calling analyze_image / describe_image so the agent can decide whether to offer a "describe this image" action. No image, no key, no cost.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/nirholas-vision-mcp/three-ws-vision-mcp#diagnostics

## Score history

- 2026-08-04: 66
- 2026-08-03: 63
- 2026-08-02: 63
- 2026-08-01: 18
- 2026-07-31: 5
- 2026-07-30: 24
- 2026-07-28: 42
- 2026-07-27: 42

## Links

- npm package: https://www.npmjs.com/package/@three-ws/vision-mcp
- Socket report: https://socket.dev/npm/package/@three-ws/vision-mcp
- Repository: https://github.com/nirholas/three.ws
- Website: https://three.ws/
- Changelog RSS feed: https://verifymcp.io/servers/nirholas-vision-mcp/three-ws-vision-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/nirholas-vision-mcp/three-ws-vision-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/nirholas-vision-mcp/three-ws-vision-mcp