# Image Gen (npm · @nuver-labs/image-gen-mcp)

Generate and edit images from your coding agent with Gemini and OpenAI, using your own API keys.

- Trust score: 77/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-13

## Components

- npm · `@nuver-labs/image-gen-mcp`: 77/100 (this document), [markdown](https://verifymcp.io/servers/com-nuverlabs-image-gen/nuver-labs-image-gen-mcp.md), [page](https://verifymcp.io/servers/com-nuverlabs-image-gen/nuver-labs-image-gen-mcp)

## Channel facts

- Registry: `npm`
- Package: `@nuver-labs/image-gen-mcp`
- Version: `0.2.1`
- 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 2026-08-13.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 47 of 136 dependencies flagged as unhealthy (1 deprecated).
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to nuver-labs/image-gen-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1376 tokens (~458/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**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add com-nuverlabs-image-gen -- npx -y @nuver-labs/image-gen-mcp
```

### Codex

```bash
codex mcp add com-nuverlabs-image-gen -- npx -y @nuver-labs/image-gen-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-nuverlabs-image-gen": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@nuver-labs/image-gen-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-nuverlabs-image-gen --command npx --arg -y --arg @nuver-labs/image-gen-mcp
```

### Hermes

```yaml
mcp_servers:
  com-nuverlabs-image-gen:
    command: "npx"
    args: ["-y", "@nuver-labs/image-gen-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "com-nuverlabs-image-gen": {
      "command": "npx",
      "args": [
        "-y",
        "@nuver-labs/image-gen-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.

### 2026-08-13 (score 77)

First indexed and scored.

## MCP tools (3)

### `generate_image` (~610 tokens)

Generate image

Generate one or more images from a text prompt using Gemini or OpenAI image models and save them to disk. Returns the absolute saved file path(s) plus provider/model metadata. Strongly prefer passing an absolute output_path inside the current project so the file lands where you can use it. Each image costs real API credits.

Input parameters:

- `aspect_ratio` (string): Gemini and OpenAI gpt-image-2 honor the ratio exactly. Older OpenAI models approximate: landscape -> 1536x1024, portrait -> 1024x1536, 1:1 -> 1024x1024.
- `background` (string): OpenAI only, ignored by Gemini. transparent yields alpha PNG/WebP, ideal for logos and icons. Requires gpt-image-1.5 or older: gpt-image-2 does not support it, so transparent calls on gpt-image-2 aut…
- `image_size` (string): Gemini 3.x models only (ignored by OpenAI; gemini-2.5-flash-image is fixed at 1024px). Default 1K.
- `model` (string): Override the model. Gemini: gemini-3.1-flash-image (default), gemini-3.1-flash-lite-image, gemini-3-pro-image, gemini-2.5-flash-image. OpenAI: gpt-image-2 (default, best quality), gpt-image-1.5, gpt-…
- `n` (integer): Number of images, 1-4 (default 1). Gemini generates sequentially, so n>1 is slower there.
- `output_path` (string): Absolute path strongly recommended. Either a full file path (.png/.jpg/.webp) or a directory (a slugified filename is derived from the prompt). If omitted: $IMAGE_GEN_MCP_OUTPUT_DIR, then $CLAUDE_PRO…
- `prompt` (string, required): What to generate. Be specific: subject, style, composition, colors, any text to render.
- `provider` (string): Override the default provider. Call list_capabilities to see what is configured.
- `quality` (string): OpenAI only, ignored by Gemini. Use low for cheap drafts.
- `return_image` (boolean): Default false. When true, also returns the FIRST image as an inline MCP image block so you can see it without a Read. Large images can exceed the MCP output token limit; for 2K/4K prefer Read on the…

### `edit_image` (~704 tokens)

Edit image

Edit or combine existing image file(s) using a text instruction: modify elements, restyle, add or remove content, or merge references. Reads the source image(s) from disk, saves the result as a NEW file (never overwrites sources), and returns the absolute saved path(s).

Input parameters:

- `aspect_ratio` (string): Gemini and OpenAI gpt-image-2 honor the ratio exactly. Older OpenAI models approximate: landscape -> 1536x1024, portrait -> 1024x1536, 1:1 -> 1024x1024.
- `background` (string): OpenAI only, ignored by Gemini. transparent yields alpha PNG/WebP, ideal for logos and icons. Requires gpt-image-1.5 or older: gpt-image-2 does not support it, so transparent calls on gpt-image-2 aut…
- `image_size` (string): Gemini 3.x models only (ignored by OpenAI; gemini-2.5-flash-image is fixed at 1024px). Default 1K.
- `input_fidelity` (string): OpenAI only. high preserves faces, logos, and fine details from the input more faithfully. Ignored on gpt-image-2, which always processes inputs at high fidelity.
- `model` (string): Override the model. Gemini: gemini-3.1-flash-image (default), gemini-3.1-flash-lite-image, gemini-3-pro-image, gemini-2.5-flash-image. OpenAI: gpt-image-2 (default, best quality), gpt-image-1.5, gpt-…
- `n` (integer): Number of images, 1-4 (default 1). Gemini generates sequentially, so n>1 is slower there.
- `output_path` (string): Absolute path strongly recommended. Either a full file path (.png/.jpg/.webp) or a directory (a slugified filename is derived from the prompt). If omitted: $IMAGE_GEN_MCP_OUTPUT_DIR, then $CLAUDE_PRO…
- `prompt` (string, required): The edit instruction, e.g. "make the background transparent" or "restyle as a flat vector logo".
- `provider` (string): Override the default provider. Call list_capabilities to see what is configured.
- `quality` (string): OpenAI only, ignored by Gemini. Use low for cheap drafts.
- `return_image` (boolean): Default false. When true, also returns the FIRST image as an inline MCP image block so you can see it without a Read. Large images can exceed the MCP output token limit; for 2K/4K prefer Read on the…
- `source_paths` (array, required): Absolute paths to existing input images (.png/.jpg/.jpeg/.webp). The first is the primary edit target; extras act as references. OpenAI accepts up to 16; Gemini works best with 1-3.

### `list_capabilities` (~62 tokens)

List image provider capabilities

Report which image providers (gemini, openai) are configured in this server, the default provider and models, known model options, the output directory fallback, and any directory restriction in force. Call this first if unsure what is available or why a call failed.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-nuverlabs-image-gen/nuver-labs-image-gen-mcp#diagnostics

## Score history

- 2026-08-13: 77

## Links

- npm package: https://www.npmjs.com/package/@nuver-labs/image-gen-mcp
- Socket report: https://socket.dev/npm/package/@nuver-labs/image-gen-mcp
- Repository: https://github.com/nuver-labs/image-gen-mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-nuverlabs-image-gen/nuver-labs-image-gen-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-nuverlabs-image-gen/nuver-labs-image-gen-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-nuverlabs-image-gen/nuver-labs-image-gen-mcp