# io.github.brajendrak00068/levea-mcp-server (npm · levea-mcp-server)

Autonomous AI video editor over MCP: viral clips, captions, reframe, chroma key, MP4 export

- Trust score: 62/100 (medium)
- Change this week: +23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `levea-mcp-server`: 62/100 (this document), [markdown](https://verifymcp.io/servers/brajendrak00068-levea-mcp-server/levea-mcp-server.md), [page](https://verifymcp.io/servers/brajendrak00068-levea-mcp-server/levea-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `levea-mcp-server`
- Version: `0.3.0`
- 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 (107 of 108), 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 (107 of 108), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL redirects; it must resolve directly.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 70 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 736 tokens (~73/item across 10 items; 10 tools + 0 resources), lean.
  - 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**: 92/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 76% 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 brajendrak00068-levea-mcp-server -- npx -y levea-mcp-server
```

### Codex

```bash
codex mcp add brajendrak00068-levea-mcp-server -- npx -y levea-mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "brajendrak00068-levea-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "levea-mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add brajendrak00068-levea-mcp-server --command npx --arg -y --arg levea-mcp-server
```

### Hermes

```yaml
mcp_servers:
  brajendrak00068-levea-mcp-server:
    command: "npx"
    args: ["-y", "levea-mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "brajendrak00068-levea-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "levea-mcp-server"
      ]
    }
  }
}
```

## 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 62, +47)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [functional regression] Security disclosure: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-08-01 (score 15, +15)

- [functional improvement] Tool coverage: unverified → 100

### 2026-07-31 (score 0, −21)

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

### 2026-07-30 (score 21, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 39)

First indexed and scored.

## MCP tools (10)

### `autonomous_edit` (~128 tokens)

PRIMARY TOOL. Run a natural-language video edit end-to-end. The agent plans, executes, verifies, and exports. Accepts anything from a one-liner ("make this TikTok-ready") to a multi-paragraph creative brief. Use this unless you specifically need a deterministic single operation.

Input parameters:

- `project_id` (string): Optional project id for tracking / continuity.
- `prompt` (string, required): Natural-language description of the desired edit or creative brief.
- `scene` (object): Optional existing scene/timeline state to continue editing.
- `video_url` (string): Optional source video URL to edit.

### `generate_viral_clips` (~129 tokens)

Extract short viral clips from a long video (engaging moments, bold captions, vertical reframe). Convenience wrapper over autonomous_edit.

Input parameters:

- `focus` (string): What to optimize for (e.g. "funny moments", "key insights").
- `max_duration` (number): Max clip length in seconds (default 60).
- `min_duration` (number): Min clip length in seconds (default 15).
- `num_clips` (number): How many clips (default 5).
- `project_id` (string)
- `video_url` (string): Source video URL.

### `add_captions` (~83 tokens)

Add styled, word-highlighted captions to the current scene (caption_compose).

Input parameters:

- `highlight_words` (array): Words to emphasize.
- `position` (string): center | top | bottom (default center).
- `project_id` (string)
- `style` (string): Caption style preset (e.g. "viral", "clean"). Default "viral".

### `remove_silence` (~70 tokens)

Remove silent gaps from the video (clean_audio, silence mode).

Input parameters:

- `min_silence_duration` (number): Min silence to cut, in ms (default 500).
- `project_id` (string)
- `silence_threshold` (number): Amplitude threshold (default 0.02).

### `read_scene` (~33 tokens)

Read the current scene / timeline state (layers, durations, metadata). Read-only.

Input parameters:

- `project_id` (string)

### `query_transcript` (~43 tokens)

Query the video transcript (search words, get timestamps). Read-only.

Input parameters:

- `project_id` (string)
- `query` (string): Text / phrase to find.

### `export_video` (~88 tokens)

Export the final video to MP4. Returns a job id; poll with check_job_status, or set wait=true to block until done.

Input parameters:

- `format` (string): Output format (default mp4).
- `project_id` (string)
- `quality` (string): standard | high | max (default standard).
- `wait` (boolean): If true, block until the export job completes.

### `check_job_status` (~63 tokens)

Check the status/progress of an async job (e.g. an export) by job id. Read-only.

Input parameters:

- `job_id` (string, required): The job id to poll.
- `wait` (boolean): If true, block until the job reaches a terminal state.

### `editor_execute` (~69 tokens)

Power-user escape hatch: invoke a specific deterministic backend tool with raw params. Prefer autonomous_edit unless you need an exact single operation. Tools are allowlisted server-side.

Input parameters:

- `params` (object): Tool-specific parameters.
- `project_id` (string)
- `tool` (string, required): Backend tool name.

### `editor_health` (~30 tokens)

Diagnostic: check connectivity to the configured backend (LEVEA_API_URL). Read-only, unauthenticated.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/brajendrak00068-levea-mcp-server/levea-mcp-server#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 62
- 2026-08-01: 15
- 2026-07-31: 0
- 2026-07-30: 21
- 2026-07-28: 39
- 2026-07-27: 39

## Links

- npm package: https://www.npmjs.com/package/levea-mcp-server
- Socket report: https://socket.dev/npm/package/levea-mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/brajendrak00068-levea-mcp-server/levea-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/brajendrak00068-levea-mcp-server/levea-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/brajendrak00068-levea-mcp-server/levea-mcp-server