# io.github.strato-space/media-gen-mcp (npm · @strato-space/media-gen-mcp)

MCP server for OpenAI Images/Videos and Google GenAI (Veo) media generation.

- Trust score: 57/100 (low)
- Change this week: +52
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-08

## Components

- npm · `@strato-space/media-gen-mcp`: 57/100 (this document), [markdown](https://verifymcp.io/servers/strato-space-media-gen-mcp/strato-space-media-gen-mcp.md), [page](https://verifymcp.io/servers/strato-space-media-gen-mcp/strato-space-media-gen-mcp)

## Channel facts

- Registry: `npm`
- Package: `@strato-space/media-gen-mcp`
- Version: `1.0.4`
- 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 2026-08-08.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects sharp 0.34.5, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 47 of 168 dependencies flagged as unhealthy (1 deprecated).
- **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 (MIT).
  - Actively maintained (last published 223 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 46/100
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 2681 tokens (~206/item across 13 items; 13 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**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 87% 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 strato-space-media-gen-mcp -- npx -y @strato-space/media-gen-mcp
```

### Codex

```bash
codex mcp add strato-space-media-gen-mcp -- npx -y @strato-space/media-gen-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "strato-space-media-gen-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@strato-space/media-gen-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add strato-space-media-gen-mcp --command npx --arg -y --arg @strato-space/media-gen-mcp
```

### Hermes

```yaml
mcp_servers:
  strato-space-media-gen-mcp:
    command: "npx"
    args: ["-y", "@strato-space/media-gen-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "strato-space-media-gen-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@strato-space/media-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.

### 2026-08-07 (score 57, +3)

- [functional] Dependency health: partial → 0.89

### 2026-08-06 (score 54, +24)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Tool coverage: 87
- [functional] First check of Schema quality: fair
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fail

### 2026-08-05 (score 30, 0)

- [security improvement] CVE-2026-69207 no longer affects this package

### 2026-08-04 (score 30, 0)

- [security regression] CVE-2026-69207 affects this package: high

### 2026-08-02 (score 30, +25)

- [security regression] GHSA-f88m-g3jw-g9cj affects this package: high
- [security regression] Provenance: unverified → fail
- [security regression] Known CVEs: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: MIT

### 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, 0)

- [functional] Schema quality: Schema quality not yet verified: our sandbox run of this package did not complete, so we have no schema to assess.
- [functional] Tool coverage: Tool coverage not yet verified: our sandbox run of this package did not complete, so we have no tool definitions to assess.

### 2026-07-28 (score 24, 0)

- [functional] Tool coverage: Tool coverage not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet.
- [functional] Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.

## MCP tools (13)

### `openai-images-generate` (~223 tokens)

OpenAI Images Generate

Generate images from text prompts using OpenAI gpt-image-1.5 (default) or gpt-image-1. Returns MCP CallToolResult with content[] (ResourceLink or ImageContent based on tool_result param) and structuredContent (OpenAI ImagesResponse format with data[].url or data[].b64_json based on response_format param).

Input parameters:

- `background` (string)
- `model` (string)
- `moderation` (string)
- `n` (integer)
- `output_compression` (integer)
- `output_format` (string)
- `prompt` (string, required)
- `quality` (string)
- `response_format` (string): Controls structuredContent shape: 'url' (default) emits data[].url, 'b64_json' emits data[].b64_json.
- `size` (string)
- `tool_result` (string): Controls content[] shape: 'resource_link' (default) emits ResourceLink items, 'image' emits base64 ImageContent blocks.
- `user` (string)

### `openai-images-edit` (~336 tokens)

OpenAI Images Edit

Edit images (inpainting, outpainting, compositing) from 1 to 16 inputs using OpenAI gpt-image-1.5 (default) or gpt-image-1. Returns MCP CallToolResult with content[] (ResourceLink or ImageContent based on tool_result param) and structuredContent (OpenAI ImagesResponse format with data[].url or data[].b64_json based on response_format param).

Input parameters:

- `image` (required): Absolute image path, base64 string, or HTTP(S) URL to edit, or an array of such values (1-16 images).
- `mask` (string): Optional absolute path, base64 string, or HTTP(S) URL for a mask image (png < 4MB, same dimensions as the first image). Fully transparent areas indicate where to edit.
- `model` (string)
- `n` (integer): Number of images to generate (1-10).
- `prompt` (string, required): A text description of the desired edit. Max 32000 chars.
- `quality` (string): Quality (high, medium, low). Default: high.
- `response_format` (string): Controls structuredContent shape: 'url' (default) emits data[].url, 'b64_json' emits data[].b64_json.
- `size` (string): Size of the generated images. Default: 1024x1536.
- `tool_result` (string): Controls content[] shape: 'resource_link' (default) emits ResourceLink items, 'image' emits base64 ImageContent blocks.
- `user` (string): Optional user identifier for OpenAI monitoring.

### `openai-videos-create` (~385 tokens)

OpenAI Videos Create

Create a video generation job using the OpenAI Videos API. Returns structuredContent with the OpenAI Video job object, and (optionally) downloaded assets as MCP content blocks (tool_result=resource_link|resource).

Input parameters:

- `download_variants` (array): Which downloadable assets to fetch when completed (default: ['video']).
- `input_reference` (string): Optional image reference: HTTP(S) URL, base64 / data URL, or file path.
- `input_reference_background`: Padding background when input_reference_fit=contain: blur (default), black, white, or hex color (#RRGGBB/#RRGGBBAA).
- `input_reference_fit` (string): How to fit input_reference to the requested video size: match (require exact), cover (crop), contain (pad), stretch (distort). Default: contain.
- `model` (string): Video model to use (default: sora-2-pro).
- `poll_interval_ms` (integer): Polling interval when wait_for_completion is true (default: 2000).
- `prompt` (string, required): Text prompt that describes the video to generate (max 32K chars).
- `seconds` (string): Clip duration in seconds (default: 4 seconds).
- `size` (string): Output resolution formatted as width x height. Sizes 1024x1792 and 1792x1024 require sora-2-pro.
- `timeout_ms` (integer): Max time to wait for completion when wait_for_completion is true (default: 900000).
- `tool_result` (string): Controls content[] shape: 'resource_link' (default) emits ResourceLink items, 'resource' emits EmbeddedResource blocks with base64 blob.
- `wait_for_completion` (boolean): If true, poll the job until completed/failed (then optionally download assets). Default: true.

### `openai-videos-remix` (~223 tokens)

OpenAI Videos Remix

Create a remix video job from an existing video_id. Returns structuredContent with the OpenAI Video job object, and (optionally) downloaded assets as MCP content blocks (tool_result=resource_link|resource).

Input parameters:

- `download_variants` (array): Which downloadable assets to fetch when completed (default: ['video']).
- `poll_interval_ms` (integer): Polling interval when wait_for_completion is true (default: 2000).
- `prompt` (string, required): Updated prompt that directs the remix (max 32K chars).
- `timeout_ms` (integer): Max time to wait for completion when wait_for_completion is true (default: 900000).
- `tool_result` (string): Controls content[] shape: 'resource_link' (default) emits ResourceLink items, 'resource' emits EmbeddedResource blocks with base64 blob.
- `video_id` (string, required): Source video job id to remix.
- `wait_for_completion` (boolean): If true, poll the job until completed/failed (then optionally download assets). Default: true.

### `openai-videos-list` (~78 tokens)

OpenAI Videos List

List video jobs using the OpenAI Videos API. Returns structuredContent with the OpenAI list response shape { data, has_more, last_id }.

Input parameters:

- `after` (string): Cursor (video id) to list after.
- `limit` (integer): Page size.
- `order` (string): Sort order of results by timestamp.

### `openai-videos-retrieve` (~36 tokens)

OpenAI Videos Retrieve

Retrieve a video job by id using the OpenAI Videos API.

Input parameters:

- `video_id` (string, required): Video job id.

### `openai-videos-delete` (~37 tokens)

OpenAI Videos Delete

Delete a video job by id using the OpenAI Videos API.

Input parameters:

- `video_id` (string, required): Video job id to delete.

### `openai-videos-retrieve-content` (~114 tokens)

OpenAI Videos Retrieve Content

Retrieve a video asset (video/thumbnail/spritesheet) for a completed job, write it under MEDIA_GEN_DIRS, and return content blocks (tool_result=resource_link|resource).

Input parameters:

- `tool_result` (string): Controls content[] shape: 'resource_link' (default) emits ResourceLink items, 'resource' emits EmbeddedResource blocks with base64 blob.
- `variant` (string): Which downloadable asset to return (default: video).
- `video_id` (string, required): Video job id.

### `google-videos-generate` (~447 tokens)

Google Videos Generate

Generate videos using Google GenAI (Veo). Can optionally wait for completion and download generated videos to MEDIA_GEN_DIRS.

Input parameters:

- `aspect_ratio` (string): Aspect ratio for the generated video.
- `download_when_done` (boolean): When waiting, whether to download generated videos to MEDIA_GEN_DIRS[0]. Defaults to true when wait_for_completion=true, otherwise false.
- `duration_seconds` (integer): Video duration in seconds (provider/model-dependent).
- `input_reference` (string): Optional image reference (image-to-video): HTTP(S) URL, base64 / data URL, or file path under MEDIA_GEN_DIRS.
- `input_reference_mime_type` (string): Optional override for input image MIME type (e.g. image/jpeg). Useful when input_reference is raw base64 without a data URL header.
- `input_video_reference` (string): Optional input video reference (video extension): HTTP(S) URL or file path under MEDIA_GEN_DIRS. Mutually exclusive with input_reference.
- `model` (string): Google video model id (default: veo-3.1-generate-001).
- `number_of_videos` (integer): Number of videos to generate (default: 1).
- `person_generation` (string): Controls whether people are allowed in the generated video.
- `poll_interval_ms` (integer): Polling interval when wait_for_completion is true (default: 10000).
- `prompt` (string): Text prompt that describes the video to generate (max 32K chars). Required unless an input image/video is provided.
- `response_format` (string): Controls structuredContent video fields: 'url' (default) prefers video.uri, 'b64_json' prefers video.videoBytes.
- `timeout_ms` (integer): Max time to wait for completion when wait_for_completion is true (default: 900000).
- `tool_result` (string): Controls content[] shape when downloading: 'resource_link' (default) emits ResourceLink items, 'resource' emits EmbeddedResource blocks with base64 blob.
- `wait_for_completion` (boolean): If true, poll the operation until done (then optionally download). Default: true.

### `google-videos-retrieve-operation` (~85 tokens)

Google Videos Retrieve Operation

Retrieve the status/result of a Google video generation operation (response_format=url|b64_json controls uri vs videoBytes in structuredContent).

Input parameters:

- `operation_name` (string, required): Google video operation name/id.
- `response_format` (string): Controls structuredContent video fields: 'url' (default) prefers video.uri, 'b64_json' prefers video.videoBytes.

### `google-videos-retrieve-content` (~145 tokens)

Google Videos Retrieve Content

Download generated video content for a completed Google video operation, write it under MEDIA_GEN_DIRS, and return content blocks (tool_result=resource_link|resource).

Input parameters:

- `index` (integer): Which generatedVideos[index] to download (default: 0).
- `operation_name` (string, required): Google video operation name/id.
- `response_format` (string): Controls structuredContent video fields: 'url' (default) prefers video.uri, 'b64_json' prefers video.videoBytes.
- `tool_result` (string): Controls content[] shape: 'resource_link' (default) emits ResourceLink items, 'resource' emits EmbeddedResource blocks with base64 blob.

### `fetch-images` (~317 tokens)

Fetch Images

Fetch and process images from URLs or local file paths. Returns MCP CallToolResult with content[] (ResourceLink or ImageContent based on tool_result param) and structuredContent (OpenAI ImagesResponse format with data[].url or data[].b64_json based on response_format param).

Input parameters:

- `compression` (object): Compression options. If omitted, no compression is applied.
- `file` (string): Base path for output files, absolute or relative to the first MEDIA_GEN_DIRS entry. If multiple images, index suffix is added.
- `ids` (array): Array of image IDs to fetch by filename match (looks for filenames containing _{id}_ or _{id}. under the primary MEDIA_GEN_DIRS[0] directory). Mutually exclusive with 'sources' and 'n'.
- `n` (integer): When set, returns the last N image files from the primary MEDIA_GEN_DIRS[0] directory (most recently modified first). Mutually exclusive with 'sources'.
- `response_format` (string): Controls structuredContent shape: 'url' (default) emits data[].url, 'b64_json' emits data[].b64_json.
- `sources` (array): Array of image sources: HTTP(S) URLs or file paths (absolute or relative to the first MEDIA_GEN_DIRS entry). Max 20 images. Mutually exclusive with 'n'.
- `tool_result` (string): Controls content[] shape: 'resource_link' (default) emits ResourceLink items, 'image' emits base64 ImageContent blocks.

### `fetch-videos` (~255 tokens)

Fetch Videos

Fetch videos from URLs or local file paths. Returns MCP CallToolResult with content blocks (tool_result=resource_link|resource) and structuredContent listing resolved files/URLs.

Input parameters:

- `file` (string): Base path for output files (when downloading from URLs), absolute or relative to the first MEDIA_GEN_DIRS entry. If multiple videos are downloaded, an index suffix is added.
- `ids` (array): Array of video IDs to fetch by filename match (looks for filenames containing _{id}_ or _{id}. under the primary MEDIA_GEN_DIRS[0] directory). Mutually exclusive with 'sources' and 'n'.
- `n` (integer): When set, returns the last N video files from the primary MEDIA_GEN_DIRS[0] directory (most recently modified first). Mutually exclusive with 'sources'.
- `sources` (array): Array of video sources: HTTP(S) URLs or file paths (absolute or relative to the first MEDIA_GEN_DIRS entry). Max 20 videos. Mutually exclusive with 'n'.
- `tool_result` (string): Controls content[] shape: 'resource_link' (default) emits ResourceLink items, 'resource' emits EmbeddedResource blocks with base64 blob.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/strato-space-media-gen-mcp/strato-space-media-gen-mcp#diagnostics

## Score history

- 2026-08-08: 57
- 2026-08-07: 57
- 2026-08-06: 54
- 2026-08-05: 30
- 2026-08-04: 30
- 2026-08-03: 30
- 2026-08-02: 30
- 2026-08-01: 5
- 2026-07-31: 5
- 2026-07-30: 24
- 2026-07-28: 24
- 2026-07-27: 24

## Links

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