# io.github.runapi-builder/luma-mcp (npm · @runapi.ai/luma-mcp)

RunAPI MCP server for Luma: create tasks, poll status, check pricing.

- Trust score: 60/100 (medium)
- Change this week: +15
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@runapi.ai/luma-mcp`: 60/100 (this document), [markdown](https://verifymcp.io/servers/runapi-builder-luma-mcp/runapi-ai-luma-mcp.md), [page](https://verifymcp.io/servers/runapi-builder-luma-mcp/runapi-ai-luma-mcp)

## Channel facts

- Registry: `npm`
- Package: `@runapi.ai/luma-mcp`
- Version: `0.1.7`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (96 of 100), 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 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 49/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 398 tokens (~99/item across 4 items; 4 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 11/100
  - Stability check failed: the tool surface changed between 0.1.6 and 0.1.7: 0 tool removals, 1 breaking changes, 0 additions.
- **Tool Coverage**: 85/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 54% 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 runapi-builder-luma-mcp -- npx -y @runapi.ai/luma-mcp
```

### Codex

```bash
codex mcp add runapi-builder-luma-mcp -- npx -y @runapi.ai/luma-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "runapi-builder-luma-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@runapi.ai/luma-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add runapi-builder-luma-mcp --command npx --arg -y --arg @runapi.ai/luma-mcp
```

### Hermes

```yaml
mcp_servers:
  runapi-builder-luma-mcp:
    command: "npx"
    args: ["-y", "@runapi.ai/luma-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "runapi-builder-luma-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@runapi.ai/luma-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.

### 2026-08-02 (score 60, +23)

- [security regression] Stability: fail → unverified
- [security regression] Provenance: fail → unverified
- [security regression] Install scripts: pass → unverified
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [functional regression] License: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Maintenance: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: Apache-2.0

### 2026-08-01 (score 37, −10)

- [security regression] Known CVEs: partial → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-31 (score 47, +23)

- [security regression] Provenance: unverified → fail
- [security regression] Malware scan: pass → unverified
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security] First check of Stability: fail
- [functional regression] Tool coverage: 64% → 54%
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional] First check of MCP protocol: pass
- [functional] Licence: Apache-2.0
- [functional] Package version: 0.1.6 → 0.1.7
- [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, −21)

- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 45)

First indexed and scored.

## MCP tools (4)

### `login` (~52 tokens)

Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.

Input parameters:

- `force` (boolean): Re-run browser login when the current credential comes from the local config file.

### `modify_video` (~109 tokens)

Create a Luma task on RunAPI (modify video). Returns a task id, status, and output URLs.

Input parameters:

- `callback_url` (string)
- `model` (string): RunAPI model slug for this model line.
- `poll_interval_ms` (integer)
- `prompt` (string, required)
- `source_video_url` (string, required)
- `timeout_ms` (integer)
- `wait` (boolean): Poll until the task reaches a terminal status.
- `watermark` (string)

### `get_task` (~62 tokens)

Fetch the current status and latest result payload for a luma task.

Input parameters:

- `action` (string): Asynchronous endpoint the task was created on. Defaults to the line's only asynchronous endpoint.
- `task_id` (string, required): Task id returned when the task was created.

### `check_pricing` (~56 tokens)

Look up RunAPI pricing for the luma model line.

Input parameters:

- `action` (string): Endpoint name. Defaults to the endpoint that offers the model.
- `model` (string): Model slug. Defaults to the line's primary model.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/runapi-builder-luma-mcp/runapi-ai-luma-mcp#diagnostics

## Score history

- 2026-08-03: 60
- 2026-08-02: 60
- 2026-08-01: 37
- 2026-07-31: 47
- 2026-07-30: 24
- 2026-07-28: 45
- 2026-07-27: 45

## Links

- npm package: https://www.npmjs.com/package/@runapi.ai/luma-mcp
- Socket report: https://socket.dev/npm/package/@runapi.ai/luma-mcp
- Repository: https://github.com/runapi-ai/luma-mcp
- Changelog RSS feed: https://verifymcp.io/servers/runapi-builder-luma-mcp/runapi-ai-luma-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/runapi-builder-luma-mcp/runapi-ai-luma-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/runapi-builder-luma-mcp/runapi-ai-luma-mcp