Openclaw Ai Video Editor MCP Server

OpenClaw AI Video Editor

An autonomous agentic video editor. Send a sentence. Get a finished video. No timelines, no keyframes, no plugin chains.

Beta. The agent can make mistakes. Preview every output before publishing or sharing. For high-stakes or irreversible edits, pass requirePlanApproval: true so the agent stops after planning and waits for your approval before anything runs.

---

Quickstart — 60 seconds

1. Get an API key. Sign up at https://studio.livecore.ai → generate an OpenClaw API key.

2. Add the MCP server to your AI client. Same npx line works for Claude Desktop, Claude Code, Cursor, Cline, OpenClaw, Hermes:

{
  "mcpServers": {
    "levea": {
      "command": "npx",
      "args": ["-y", "levea-mcp-server"],
      "env": {
        "LEVEA_API_URL": "https://api.livecore.ai",
        "LEVEA_API_KEY": "your-key-from-studio.livecore.ai"
      }
    }
  }
}

One-liners for specific clients:

• Claude Code: claude mcp add levea -e LEVEA_API_URL=https://api.livecore.ai -e LEVEA_API_KEY=... -- npx -y levea-mcp-server
• OpenClaw: openclaw mcp add levea --command "npx -y levea-mcp-server" --env LEVEA_API_URL=https://api.livecore.ai --env LEVEA_API_KEY=...
• Hermes: see hermes-levea/

3. Use it. Once registered, say to your AI: "Use the levea tool to generate 5 viral clips from this video, add captions, reframe vertical." The agent picks the tool, fills the prompt, the editor plans + executes + exports.

Hosts (don't confuse)

The client appends /api/v1/misc/openclaw/v1/execute automatically; never set a full path in LEVEA_API_URL.

Tools the AI sees (10)

autonomous_edit (primary — free-form prompt) · generate_viral_clips · add_captions · remove_silence · read_scene · query_transcript · export_video · check_job_status · editor_execute (allowlisted backend escape hatch) · editor_health

→ For AI-agent integration details (schemas, async semantics, error handling, plan approval), see AGENTS.md.

Live channels

On the currently-published npm v0.2.0 the env vars are named ADSCENE_API_URL / ADSCENE_API_KEY. v0.3.0 (in this repo, pending republish) accepts both names — LEVEA_* is canonical, ADSCENE_* kept as silent fallback so existing configs don't break.

---

Works in every AI client (MCP-first)

The portable interface is the levea-mcp-server MCP server. One server, every MCP client — Claude Desktop, Claude Code, Cursor, Cline, OpenClaw, Hermes — with one tool surface backed by one backend contract, so nothing drifts per platform.

The OpenClaw plugin below remains for chat-native UX and ClawHub discoverability; it and every other client call the same backend.

---

Beyond one-liners: goals and briefs

autonomous_edit accepts anything from a five-word command to a five-hundred-word creative brief. Three flavors:

1. Direct commands

Single edit, single result:

"Generate captions and remove silences"
"Reframe to 9:16 for TikTok"
"Color grade like a Netflix doc"

2. Open-ended goals (watch and propose)

Hand the agent a goal instead of a command and it inspects the asset, then proposes a plan:

"Watch this and tell me how to make it more engaging for TikTok"
"Look at the first 30 seconds and suggest 3 ways to hook the viewer"
"Review this footage and propose edits to tighten the pacing"

Pair these with requirePlanApproval: true to keep the agent in propose-only mode — it stops after planning, returns the full plan, and waits for your approval before executing anything.

3. Full creative briefs

Multi-step orchestrations executed end-to-end. The agent decomposes the brief into a DAG of canonical actions, plans the order, executes through safety gates, verifies each step, and exports every requested format. Use SSE to watch each step land in real time.

Transform this video into a viral social media documentary. Start by trimming the first 3 seconds and last 5 seconds to remove dead air. Apply a cinematic color grade with warm tones and high contrast. Generate auto-captions with bold yellow text and black outline, positioned at the bottom center. Add a dynamic zoom-in effect on the main subject during the first 10 seconds. Insert 3 contextual b-roll clips at moments where the speaker mentions visual concepts. Apply face tracking to keep the subject centered when converting to vertical 9:16 format for TikTok and Instagram Reels. Add an upbeat background music track that matches the energy, with auto-ducking when the speaker talks. Remove all silence gaps longer than 0.5 seconds to tighten pacing. Apply a subtle vignette effect around the edges. Add my logo watermark in the top right corner with 80% opacity. Generate a custom thumbnail with the most expressive frame and bold text overlay saying MUST WATCH. Create an animated subscribe button that appears at 5 seconds and pulses. Add sound effects for emphasis at key moments - use whoosh sounds for transitions. Apply noise reduction to clean up the audio. Split the video at 30 seconds to insert a 2-second transition effect. Add text overlays for key statistics mentioned in the video with animated counter effects. Apply motion tracking to blur any faces in the background for privacy. Export the final video in 1080p for YouTube and also create optimized versions for TikTok, Instagram Reels, and YouTube Shorts with platform-specific aspect ratios and durations.

That single call composes ~20 canonical actions in one planned run. No timeline UI, no per-step API calls, no glue code on your side.

---

What you can do with it

That's the headline. Below is the full surface.

Beta caveat: outputs sometimes need a second pass. Preview before publishing; for anything you can't undo, approve the plan first using the plan approval flow.

---

Made for

• Creators & influencers — turn long videos into TikToks, Reels, Shorts; auto-captions; viral-clip generation; AI thumbnails
• Podcasters — video-podcast highlights, audiograms, multi-cam podcast editing, silence and filler-word removal
• Marketers & agencies — ad creation at scale, social-first repurposing, brand-overlay automation, multi-platform exports
• Educators & course creators — tutorial editing, auto-chapters, OCR'd slide titles, auto-captions, word-level emphasis
• YouTubers — long-form → Shorts pipeline, thumbnail generation, intro / outro automation, chapter markers
• Sales & SaaS — product demos, walkthrough highlights, voiceover narration with cloned voices
• Event teams — webinar / conference highlights, multi-cam stitching, speaker spotlight reels
• Faith & community — sermon clips for social, message highlights, multi-platform packaging

---

Capability surface

Read & inspect

• Inspect the timeline structure, layer properties, and scene state
• Search the asset gallery by type, duration, name
• Run computer-vision analysis on frames (object, face, scene)
• Extract on-screen text — OCR of chyrons, lower-thirds, slide titles, captions burned into source
• Search the transcript by keyword, semantic meaning, or timestamp window
• Pull video intelligence — narrative peaks, speaker diarization, sentiment, pacing
• Poll async job status, introspect tool / schema metadata

Structural editing

• Insert / update / replace / delete layers — video, audio, text, image, shape, group, adjustment
• Trim, split, retime — slow-motion (0.5×), fast-forward (2×), freeze-frame, ramp curves
• Reposition, sequence, snap to transcript word boundaries
• Heal timeline gaps, normalize audio, reconcile durations (pre-export safety pass)
• Multi-step undo / redo

Visual editing

• Color grading — brightness, contrast, saturation, hue, lift / gamma / gain, RGB curves
• Procedural VFX shaders — smoke, dust, fire, explosion, lightning, snow, glitch, scanlines, grain, glassmorphism, bokeh, lava, telomere / corrosion, portal
• Chroma key — green / blue screen with similarity, smoothness, spill suppression
• AI background removal — alpha matte (works on any video, no green screen required)
• AI background blur — subject-aware depth blur
• Object removal — (roadmap) AI mask + inpaint
• Masking — luma, alpha, depth masks
• Geometric clip shapes — circle, dome, star, hexagon, polygon
• Crop — absolute or edge-based; 3D rotation + perspective
• Glow, shadow, inner shadow, gradient fills, text gradients
• Vertical reframe (9:16) and vertical-reframe montage — caption-safe (avoids cropping through on-screen text and chyrons)
• Split screen — top/bottom, left/right, picture-in-picture, grid
• Branding overlays — logo / watermark from gallery or AI-generated
• Motion / face tracking with dynamic zoom-follow framing

Captions & text

• Auto-generate captions from the transcript
• Style captions with built-in templates or an AI director that picks / generates a custom template at runtime
• Curved text paths — circle, wave, custom SVG
• Per-word animations — typewriter, slide, fade, scale, rotate, bounce, flip, swing, elastic, blur, glitch, wave (each with matching exit)
• Lottie animation playback control

Audio

• Clean audio — remove silences, breaths, filler words; word-level mute / cut
• Auto-ducking on speech detection (sidechain music vs voice)
• Mix / normalize / denoise / EQ (bass-boost, vocal-clarity, warm, bright presets)
• Sync external master audio to video (offset, mute camera audio)
• Beat-synced cuts — provide beat_times or bpm, the editor aligns cuts
• Add SFX
• Generate music (mood / genre / BPM)
• Generate voiceover (TTS or cloned voice)
• Render waveform visualizers (bars, wave, circular)

Async generation

• AI video / B-roll — duration + aspect ratio
• AI images — single or batch at timestamps
• AI music — prompt + duration + mood + genre + BPM
• AI voiceover — TTS or cloned voice library
• Auto-thumbnail extraction
• Face blur — all faces or background-only
• Image edit — generative instruction-based

High-level presets

Each preset bundles many underlying edits into a single call:

Export

---

How you use it

Every edit goes through one tool: autonomous_edit. Pass a natural-language description of what you want and the agent plans, executes, verifies, and exports — no tool list to memorize, no structured params to learn.

curl -sS -X POST "$LEVEA_API_URL/api/v1/misc/openclaw/v1/execute" \
  -H "Authorization: Bearer $LEVEA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tool": "autonomous_edit",
    "params": {
      "prompt": "Make this a TikTok-ready viral clip: vertical reframe, add bold captions, remove silences, motion-track the speaker, and export."
    },
    "project_id": "my-project"
  }'

Anything in the capability surface above is reachable from a prompt. Mix and match: chroma key + background replace + caption + emphasis in a single sentence works.

---

Quick start

1. Get an API key

Sign up at https://studio.livecore.ai/ and generate an OpenClaw API key from the account UI.

2. Install the plugin

openclaw plugins install clawhub:openclaw-ai-video-editor

Or via npm:

npm install openclaw-ai-video-editor

3. Configure

export LEVEA_API_URL="https://api.livecore.ai"
export LEVEA_API_KEY="your-openclaw-api-key"

Or in OpenClaw skill config:

{
  "skills": {
    "entries": {
      "openclaw_ai_video_editor": {
        "enabled": true,
        "env": {
          "LEVEA_API_URL": "https://api.livecore.ai",
          "LEVEA_API_KEY": "your-openclaw-api-key"
        }
      }
    }
  }
}

4. Run an autonomous edit

curl -sS -X POST "$LEVEA_API_URL/api/v1/misc/openclaw/v1/execute" \
  -H "Authorization: Bearer $LEVEA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tool": "autonomous_edit",
    "params": {
      "prompt": "Generate 5 viral clips, 15-30 seconds each, focused on the most engaging moments. Add bold captions, vertical reframe, remove silences."
    },
    "project_id": "my-project"
  }'

---

API surface

Base URL: {LEVEA_API_URL} (production: https://api.livecore.ai)

Auth header:

Authorization: Bearer {LEVEA_API_KEY}

Do not set LEVEA_API_URL to https://studio.livecore.ai or the in-product editor route /api/v1/misc/editor/. Studio is the user-facing app; OpenClaw requests go to the API-key route on https://api.livecore.ai.

Request body

{
  "tool": "autonomous_edit",
  "params": { "prompt": "<natural-language edit>" },
  "project_id": "optional",
  "scene": { }
}

JSON response

{
  "type": "success" | "partial_success",
  "tool": "<tool-name>",
  "success": true,
  "status": "completed" | "failed" | "awaiting_approval",
  "scene": { },
  "reply": "Human-readable summary of what changed",
  "videoUrl": "https://.../output.mp4",
  "jobId": "task_...",
  "viral_clips": [ ],
  "zip_url": "https://.../clips.zip",
  "activeTasks": [ ],
  "pendingAsyncJobs": [ ],
  "verificationPassed": true,
  "verificationIssues": [],
  "processingTime": 12.3,
  "workingMemory": { }
}

SSE streaming

Set Accept: text/event-stream or ?stream=true. Notable event types:

Async job lifecycle

Generation actions return immediately with a jobId. Poll:

curl -sS "$LEVEA_API_URL/api/v1/misc/openclaw/v1/jobs/$JOB_ID" \
  -H "Authorization: Bearer $LEVEA_API_KEY"

Auto-export

After any mutating tool call, if the scene actually changed and an export isn't already queued, the route auto-fires one as a second run. Read-only and conversational autonomous_edit calls do not trigger auto-export.

Plan approval flow

Pass requirePlanApproval: true to make the agent stop after planning. It returns status: "awaiting_approval" + populated workingMemory. Resume by sending the same workingMemory with an approval prompt (yes, approve, go, do it, confirm).

---

How this differs from legacy editors

This isn't an editor with AI features bolted on. It's an autonomous agent that finishes the edit for you.

---

Safety & limits

• Currently in beta — outputs can be wrong. Preview every result before sharing or publishing. For irreversible workflows, pass requirePlanApproval: true to inspect and approve the plan before any edit runs.
• API-key authentication on every request
• Destructive actions (mass deletes, clears) require explicit confirmation params
• Output is verified after execution; auto-repairs on failure
• Concurrent identical requests are deduplicated server-side
• Rate-limited per API key. Read-only ~1–3s, structural edits ~3–10s, async generation 30s–5min per artifact, viral-clip / multi-platform exports several minutes

---

Supported media

---

End-to-end example: viral-clip generation

# 1) Kick off the viral-clip pipeline
curl -sS -X POST "$LEVEA_API_URL/api/v1/misc/openclaw/v1/execute" \
  -H "Authorization: Bearer $LEVEA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tool": "autonomous_edit",
    "params": {
      "prompt": "Generate 5 viral clips, 15-30 seconds each, focused on the most engaging moments. Add bold captions, vertical reframe, remove silences."
    },
    "project_id": "my-project"
  }' | tee /tmp/result.json | jq -r '.jobId // .activeTasks[0].intent.job_id'

# 2) Poll job status until done
JOB_ID=$(jq -r '.jobId // .activeTasks[0].intent.job_id' /tmp/result.json)
while true; do
  STATUS=$(curl -sS "$LEVEA_API_URL/api/v1/misc/openclaw/v1/jobs/$JOB_ID" \
    -H "Authorization: Bearer $LEVEA_API_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  [ "$STATUS" = "completed" ] || [ "$STATUS" = "failed" ] && break
  sleep 5
done

# 3) Fetch the final artifact URLs
curl -sS "$LEVEA_API_URL/api/v1/misc/openclaw/v1/jobs/$JOB_ID" \
  -H "Authorization: Bearer $LEVEA_API_KEY" | jq '.result'

---

Links

• ClawHub plugin — clawhub.ai/plugins/openclaw-ai-video-editor
• ClawHub skill (agentic) — clawhub.ai/skills/ai-agentic-video-editor
• ClawHub skill (Levea brand) — clawhub.ai/skills/levea-ai-video-editor
• npm (MCP server) — npmjs.com/package/levea-mcp-server
• MCP Registry — io.github.brajendrak00068/levea-mcp-server (registry)
• Sign up + API keys — studio.livecore.ai
• API base — https://api.livecore.ai

Support

Setup help, integration questions, or issue reports — brajendrak00068@gmail.com

License

MIT