Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

io.github.brajendrak00068/levea-mcp-server

NPM · LEVEA-MCP-SERVER · SCANNED AUG 3

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

Available components

+23 this week 62 Trust /100
Trust breakdown (6 categories)

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. How we score →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (107 of 108), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (107 of 108), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency19
Schema Quality & AI Usability70
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 736 tokens (~73/item across 10 items; 10 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage92
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 76% of tool parameters carry a description.Partial
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · levea-mcp-server

# add to Claude Code
claude mcp add brajendrak00068-levea-mcp-server -- npx -y levea-mcp-server
# add to Codex CLI
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
    }
  }
}
# add to OpenClaw
openclaw mcp add brajendrak00068-levea-mcp-server --command npx --arg -y --arg levea-mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  brajendrak00068-levea-mcp-server:
    command: "npx"
    args: ["-y", "levea-mcp-server"]
// mcp.json
{
  "mcpServers": {
    "brajendrak00068-levea-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "levea-mcp-server"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 2 Aug 26 +47
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Security disclosure: fail → unverified functional
    • Tool coverage: 100 → unverified functional
    • License: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Stability: unverified → 0.23 functional
    • Schema quality: unverified → good functional
    • Licence: MIT functional
  • 1 Aug 26 +15
    • Tool coverage: unverified → 100 functional
  • 31 Jul 26 −21
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 −18
    • Malware scan: pass → unverified security
  • 27 Jul 26 39

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 107 packages

107 packages in the resolved dependency tree · 107 deprecated · 32 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 10 exposed · ~736 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
add_captions ~83

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

NameTypeReqDescription
highlight_wordsarrayWords to emphasize.
positionstringcenter | top | bottom (default center).
project_idstring
stylestringCaption style preset (e.g. "viral", "clean"). Default "viral".

No output schema declared.

No examples provided.

autonomous_edit ~128

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.

NameTypeReqDescription
project_idstringOptional project id for tracking / continuity.
promptstringyesNatural-language description of the desired edit or creative brief.
sceneobjectOptional existing scene/timeline state to continue editing.
video_urlstringOptional source video URL to edit.

No output schema declared.

No examples provided.

check_job_status ~63

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

NameTypeReqDescription
job_idstringyesThe job id to poll.
waitbooleanIf true, block until the job reaches a terminal state.

No output schema declared.

No examples provided.

editor_execute ~69

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.

NameTypeReqDescription
paramsobjectTool-specific parameters.
project_idstring
toolstringyesBackend tool name.

No output schema declared.

No examples provided.

editor_health ~30

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

export_video ~88

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

NameTypeReqDescription
formatstringOutput format (default mp4).
project_idstring
qualitystringstandard | high | max (default standard).
waitbooleanIf true, block until the export job completes.

No output schema declared.

No examples provided.

generate_viral_clips ~129

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

NameTypeReqDescription
focusstringWhat to optimize for (e.g. "funny moments", "key insights").
max_durationnumberMax clip length in seconds (default 60).
min_durationnumberMin clip length in seconds (default 15).
num_clipsnumberHow many clips (default 5).
project_idstring
video_urlstringSource video URL.

No output schema declared.

No examples provided.

query_transcript ~43

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

NameTypeReqDescription
project_idstring
querystringText / phrase to find.

No output schema declared.

No examples provided.

read_scene ~33

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

NameTypeReqDescription
project_idstring

No output schema declared.

No examples provided.

remove_silence ~70

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

NameTypeReqDescription
min_silence_durationnumberMin silence to cut, in ms (default 500).
project_idstring
silence_thresholdnumberAmplitude threshold (default 0.02).

No output schema declared.

No examples provided.