EditVideo Agent
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
EditVideo Agent
Senses, hands and composition skills that let an AI edit video. EditVideo Agent is an MCP server and CLI that gives Claude, Codex or any MCP client the ability to read footage and audio, edit a revision-locked timeline or the generated source code, render with Remotion or HyperFrames, and check the result with measurements, then iterate.
It is not a video editor for people and has no studio UI. The calling model makes the editorial and aesthetic decisions; the runtime executes them deterministically and returns evidence (frames, crops, audio, numbers). There is no hidden beauty score and no approval gate. Tiếng Việt: README.vi.md.

Start here
Try it: INSTALL.md, then
python scripts/demo.py --render, then docs/SPEC.md for what the parts are.From an AI host: there is no need to load 137 tool schemas or the docs.
editvideo_bootstrap(task)returns the few tools and the one guide a task needs;editvideo_discover_tools(query, include_schema=true)gives exact schemas on demand;EDITVIDEO_TOOLSET=compactexposes 7 entry tools to small-context hosts.Find a guide: docs/README.md lists the guides by task. Names like "round 6" in older pages and test files record how the system was built; you do not need them.
Contribute: CONTRIBUTING.md.
v0.8.0 + unreleased upgrades: 137 MCP tools · 95 runnable effects (each with a before/after preview strip in both engines) + 7 tested combos · 18 layer kinds · 17 explainer recipes + 4 title recipes · 16 Vietnamese-complete font families · 24 palettes · 17 style kits · 7 original LUTs plus a scene-referred colour graph.
Related MCP server: video-editor
What the AI gets
Capabilities | |
Senses | Index and inspect video windows with real frames and audio blocks; crops with exact coordinate mapping; transcripts with word timing; audio events; music tempo, sections, hits and beat-fit; dialogue reading (speakers, pauses, filler candidates); edit-event profile (cuts, punch-ins, overlay pops); motion audit (static spans, judder, frozen endings, baked letterbox bars); colour statistics, scopes and shot consistency; planar and region tracking; reference-video study. |
Hands | Revision-locked timeline patches (shots, layers, keyframes, transitions, audio); expressions as data — track modifiers (loop, inertia, wiggle), follow-through, drivers (link any track to another) and two-bone IK; masks, track mattes, chroma key, corner pin / screen replacement; native 3D scenes (glTF, lights, keyed spots, turntables); a scene-referred colour graph (camera log → ACEScct grading → Cineon print look under the output transform → display, with tracked windows); retime, stabilise, reframe; dialogue condensing with room tone; multicam sync and switching; aspect adaptation (9:16, 4:5, 1:1); optional GPU tools (SAM 2 masks, LaMa/ProPainter inpainting, local LTX footage). |
Composition skills | Recipes that compile to editable layers: titles (impact cards, lockups, word cards, sound-first), explainers (diagrams, plots, unit grids, camera stages, documentary time cards, evidence_3d), professional edit recipes, ad and trailer planning/audits, direction cards, a design library with glyph-measured layout (including ink-measured line height for stacked Vietnamese diacritics). |
Learning from successful work |
|
Craft memory |
|
Shorts and films |
|
Self-review |
|
Token economy. Tool I/O is compacted at the protocol edge: compact JSON with rounded floats, slimmed schemas, no
duplicate structured copy, catalogs that list one-line rows until an exact id is asked for, handles (track_id,
manifests) instead of dumps, and image packets whose text carries only evidence ids. EDITVIDEO_TOOLSET=compact
exposes 7 entry tools for small-context hosts. See docs/AI_ERGONOMICS.md.
Demo
EditVideo Agent in 89 seconds (1080p, 51 MB, from the release page; a small 720p preview is in the repository): the tools at work, full frame. It finds and follows a subject, cuts to music, explains with 3D and motion graphics, renders 3D, grades colour, builds history from the archive and checks its own work. Each chapter names the MCP tools that made it; the footage is real and credited. Chapter by chapter: docs/demo.
Three short archive films built end to end by the system from public-domain material (720p previews):
|
|
|
Leo thang 1964-1968: | Lan rộng 1965-1968: | Vịnh Bắc Bộ 1964: |
Quick start
Requirements: Python 3.11+, Node.js 22+, FFmpeg/FFprobe on PATH. Windows is the tested platform; setup.sh covers the
core runtime on Linux/macOS (less tested). The full guide, with prerequisites, optional extras, client configuration
and troubleshooting, is INSTALL.md (tiếng Việt); what the system is and its contracts:
docs/SPEC.md.
./setup.ps1 # core: Python venv, engines (npm ci), writes .mcp.json for this clone
./setup.ps1 -Vision # + SAM 2 / depth / LaMa (CUDA, ~2.5 GB)
./setup.ps1 -Temporal # + ProPainter and local LTX footage
./setup.ps1 -Voice # + offline Vietnamese narration: Piper (GPL-3.0, separate process), vi_VN voice and Whisper small for word timing (~580 MB)Claude Code: open the folder; .mcp.json (written by setup from .mcp.example.json) registers the
server, and the skill lives in .claude/skills/editvideo-agent.
Codex: skill in .agents/skills/editvideo-agent; add the server:
[mcp_servers.editvideo]
command = '<repo>\.venv\Scripts\python.exe'
args = ['<repo>\run.py']Start every session with editvideo_bootstrap(task) → editvideo_discover_tools(query, include_schema=true). The
bootstrap reports the server version and tool count so a stale client connection is easy to spot. One-shot CLI:
echo '{"tool":"editvideo_list_projects","arguments":{}}' | python run.py --cli.
Verify
python -m pip install -r requirements-dev.txt
python -m pytest -qAbout 600 tests run in about 15 minutes on CPU (FFmpeg, Node and the Remotion Chromium are needed; GPU model tests only
run with EDITVIDEO_RUN_RUNTIME_TESTS=1, and tests of optional extras skip when the extra is not installed). The suite
uses its own temporary data store. Synthetic ground-truth generators (tests/synth_*.py) check music, dialogue and
multicam analysis against known answers.
Repository layout
editvideo/ MCP server, timeline model, perception, recipes, colour, audio, review
engines/ Remotion entry (AgentVideo.tsx), HyperFrames runtime, shared effects.js / scene3d.js
assets/ bundled fonts (with licences), original LUTs, vendored library previews
.claude/ .agents/ skills for Claude Code and Codex; the independent reviewer agent
docs/ guides (workflows, colour/3D, explainer kit, review rubric, research log)
examples/ reference build scripts (the sample films)
scripts/ setup helpers, atlas builders, repo facts
tests/ pytest suite and synthetic ground-truth generatorsRuntime state (data/) and renders (outputs/) stay local and are git-ignored; publish chosen renders as release
assets.
Documentation
Install · Documentation map · Specification · Demo films · Pro workflows · Explainer kit · Colour, depth & 3D · Design library · Model integration · AI ergonomics · Review rubric · Learning from references · Changelog · Contributing · Code of conduct · Security
Licence
EditVideo Agent is licensed under the Apache License 2.0 (NOTICE). The engines, fonts, models, data and media it uses keep their own licences: see THIRD_PARTY_NOTICES.md.
Remotion is free for individuals and small companies, but larger for-profit organisations need a Remotion company licence. HyperFrames (Apache-2.0) is the open engine.
ProPainter is non-commercial.
Piper (GPL-3.0) runs as a separate process.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
AI video editor for agents and humans: timeline, captions, color, audio and generation as MCP tools.
MCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.
Hosted video MCP server for branded explainers and reference-driven edits.
MCP server for Wan AI video generation
Related MCP Servers
- FlicenseAqualityDmaintenanceAn MCP server that transforms LLM-enabled IDEs into professional video editors by pre-processing footage into text proxies, generating motion graphics via HTML/CSS, and orchestrating complex FFmpeg renders.4-
- AlicenseNot gradedqualityDmaintenanceAn MCP server for programmatic video editing using ffmpeg, enabling draft creation and refinement via natural language.15 npmISC
- AlicenseNot gradedqualityCmaintenanceAn MCP server for creative generation and video production, letting AI agents author declarative animations, render deterministic frames, and measure output quality with perception instruments for brand and accessibility conformance.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceMCP server for OpenChatCut, enabling AI agents to create, edit, and export fully editable video projects through a real multitrack timeline and agent-native tools.1AGPL 3.0


