Metadata-Version: 2.4
Name: mcp-video
Version: 1.3.7
Summary: Video editing MCP server for AI agents. 91 FFmpeg, creation, and Hyperframes tools, Python client, and CLI. Local, fast, free.
Project-URL: Homepage, https://kyanitelabs.github.io/mcp-video/
Project-URL: Documentation, https://github.com/KyaniteLabs/mcp-video#readme
Project-URL: Repository, https://github.com/KyaniteLabs/mcp-video
Project-URL: Bug Tracker, https://github.com/KyaniteLabs/mcp-video/issues
Project-URL: Changelog, https://github.com/KyaniteLabs/mcp-video/blob/master/CHANGELOG.md
Project-URL: Discussions, https://github.com/KyaniteLabs/mcp-video/discussions
License-Expression: Apache-2.0
License-File: LICENSE
Keywords: agents,ai,ai-video,chroma-key,claude,claude-code,cli,codex,color-grading,cursor,editing,ffmpeg,hyperframes,mcp,mcp-server,model-context-protocol,stabilization,subtitle,subtitles,transcription,video,video-automation,video-processing,whisper
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Natural Language :: English
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Multimedia :: Sound/Audio
Classifier: Topic :: Multimedia :: Video
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Typing :: Typed
Requires-Python: >=3.11
Requires-Dist: mcp>=1.27.0
Requires-Dist: pydantic>=2.13.2
Requires-Dist: rich>=15.0.0
Provides-Extra: ai
Requires-Dist: basicsr>=1.4; extra == 'ai'
Requires-Dist: demucs>=4.0; extra == 'ai'
Requires-Dist: imagehash>=4.3; extra == 'ai'
Requires-Dist: numpy>=2.0.0; extra == 'ai'
Requires-Dist: openai-whisper>=20231117; extra == 'ai'
Requires-Dist: opencv-contrib-python>=4.10; extra == 'ai'
Requires-Dist: pillow>=10.0; extra == 'ai'
Requires-Dist: realesrgan>=0.3; extra == 'ai'
Requires-Dist: torch>=2.0; extra == 'ai'
Requires-Dist: torchaudio>=2.0; extra == 'ai'
Provides-Extra: ai-scene
Requires-Dist: imagehash>=4.3; extra == 'ai-scene'
Requires-Dist: pillow>=10.0; extra == 'ai-scene'
Provides-Extra: all-ai
Requires-Dist: basicsr>=1.4; extra == 'all-ai'
Requires-Dist: demucs>=4.0; extra == 'all-ai'
Requires-Dist: imagehash>=4.3; extra == 'all-ai'
Requires-Dist: numpy>=2.0.0; extra == 'all-ai'
Requires-Dist: openai-whisper>=20231117; extra == 'all-ai'
Requires-Dist: opencv-contrib-python>=4.10; extra == 'all-ai'
Requires-Dist: pillow>=10.0; extra == 'all-ai'
Requires-Dist: realesrgan>=0.3; extra == 'all-ai'
Requires-Dist: torch>=2.0; extra == 'all-ai'
Requires-Dist: torchaudio>=2.0; extra == 'all-ai'
Provides-Extra: client
Requires-Dist: pillow>=10.0; extra == 'client'
Provides-Extra: dev
Requires-Dist: pillow>=10.0; extra == 'dev'
Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Requires-Dist: rich>=15.0.0; extra == 'dev'
Requires-Dist: ruff>=0.15.11; extra == 'dev'
Requires-Dist: scikit-learn>=1.3; extra == 'dev'
Requires-Dist: webcolors>=1.13; extra == 'dev'
Provides-Extra: hyperframes
Provides-Extra: image
Requires-Dist: pillow>=10.0; extra == 'image'
Requires-Dist: scikit-learn>=1.3; extra == 'image'
Requires-Dist: webcolors>=1.13; extra == 'image'
Provides-Extra: image-ai
Requires-Dist: anthropic>=0.96.0; extra == 'image-ai'
Requires-Dist: pillow>=10.0; extra == 'image-ai'
Requires-Dist: scikit-learn>=1.3; extra == 'image-ai'
Requires-Dist: webcolors>=1.13; extra == 'image-ai'
Provides-Extra: stems
Requires-Dist: demucs>=4.0; extra == 'stems'
Requires-Dist: torch>=2.0; extra == 'stems'
Requires-Dist: torchaudio>=2.0; extra == 'stems'
Provides-Extra: transcribe
Requires-Dist: openai-whisper>=20231117; extra == 'transcribe'
Provides-Extra: upscale
Requires-Dist: basicsr>=1.4; extra == 'upscale'
Requires-Dist: numpy>=2.0.0; extra == 'upscale'
Requires-Dist: opencv-contrib-python>=4.10; extra == 'upscale'
Requires-Dist: pillow>=10.0; extra == 'upscale'
Requires-Dist: realesrgan>=0.3; extra == 'upscale'
Requires-Dist: torch>=2.0; extra == 'upscale'
Description-Content-Type: text/markdown

<p align="center">
  <a href="https://kyanitelabs.tech">
    <img src="https://kyanitelabs.tech/static/brand/hero_crystal_workbench_1672x941.png" alt="Kyanite Labs AI tool workbench hero image" width="100%">
  </a>
</p>

<!-- mcp-name: io.github.KyaniteLabs/mcp-video -->

<h1 align="center">mcp-video</h1>

<p align="center">
  <strong>Video editing MCP server for AI agents.</strong><br>
  91 structured tools for FFmpeg video editing, cinematic prompt planning, media analysis, subtitles, audio, effects, and Hyperframes video creation.
</p>

<p align="center">
  <a href="https://pypi.org/project/mcp-video/"><img src="https://img.shields.io/pypi/v/mcp-video.svg" alt="PyPI"></a>
  <a href="https://github.com/KyaniteLabs/mcp-video/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/KyaniteLabs/mcp-video/.github/workflows/ci.yml?branch=master&label=CI" alt="CI"></a>
  <img src="https://img.shields.io/badge/MCP-91%20tools-orange.svg" alt="91 MCP tools">
  <img src="https://img.shields.io/badge/python-3.11%2B-blue.svg" alt="Python 3.11+">
  <img src="https://img.shields.io/badge/license-Apache%202.0-blue.svg" alt="Apache 2.0">
</p>

<p align="center">
  <a href="#install">Install</a> &bull;
  <a href="#quick-start">Quick Start</a> &bull;
  <a href="#what-agents-can-do">Agent Workflows</a> &bull;
  <a href="#tool-surface">Tools</a> &bull;
  <a href="docs/TOOLS.md">Tool Reference</a> &bull;
  <a href="docs/AI_AGENT_DISCOVERY.md">AI Discovery</a> &bull;
  <a href="llms.txt">llms.txt</a>
</p>

---

## Public Discovery

**mcp-video** is a free, open-source **Model Context Protocol (MCP) server**, Python library, and CLI that gives AI agents a real video-editing surface. It wraps FFmpeg, cinematic style-pack/storyboard planning, media analysis, quality checks, subtitles, audio generation, effects, and code-driven Hyperframes rendering behind structured tool schemas.

Best-fit searches:

- video editing MCP server
- AI agent video editing
- FFmpeg MCP tools
- Claude Code video editing
- Cursor MCP video tools
- Python video editing library
- subtitle automation
- reels and shorts automation
- agentic media pipeline
- local AI video workflow

## Why It Exists

AI agents can write FFmpeg commands, but they should not have to guess flags, parse brittle stderr, or silently publish broken media. mcp-video gives agents typed operations, inspectable tool metadata, structured results, and quality checkpoints so a video workflow can be automated and reviewed without turning into shell-command roulette.

Use it when you want an AI assistant to:

- trim, merge, resize, crop, rotate, transcode, or export video;
- add text, subtitles, watermarks, overlays, filters, fades, effects, and transitions;
- extract audio, normalize audio, synthesize audio, add generated audio, or create waveforms;
- detect scenes, make thumbnails, generate storyboards, compare quality, and create release checkpoints;
- scaffold cinematic projects, read STYLE_/NEG_ blocks, parse storyboard tables, and expand shot prompts;
- create new video projects with Hyperframes and post-process the result with FFmpeg tools;
- drive repeatable media workflows from Claude Code, Cursor, Codex-style clients, scripts, or CI.

## Installation

Prerequisite: [FFmpeg](https://ffmpeg.org/) must be installed and available on `PATH`.

```bash
# macOS
brew install ffmpeg

# Ubuntu/Debian
sudo apt install ffmpeg
```

Run without a global install:

```bash
uvx --from mcp-video mcp-video doctor
```

Or install with pip:

```bash
pip install mcp-video
mcp-video doctor
```

Hyperframes tools additionally need Node.js 22+ because they call the Hyperframes CLI through `npx`.

## Quick Start

### Claude Code

```bash
claude mcp add mcp-video -- uvx --from mcp-video mcp-video
```

### Claude Desktop

```json
{
  "mcpServers": {
    "mcp-video": {
      "command": "uvx",
      "args": ["--from", "mcp-video", "mcp-video"]
    }
  }
}
```

### Cursor

```json
{
  "mcpServers": {
    "mcp-video": {
      "command": "uvx",
      "args": ["--from", "mcp-video", "mcp-video"]
    }
  }
}
```

Then ask your agent:

> Trim this interview into a 45-second vertical clip, add burned captions, normalize the audio, make a thumbnail, and create a release checkpoint before export.

## Python Client

```python
from mcp_video import Client

editor = Client()

clip = editor.trim("interview.mp4", start="00:02:15", duration="00:00:45")
caption_file = "captions.srt"
editor.ai_transcribe(clip.output_path, output_srt=caption_file)
captioned = editor.subtitles(clip.output_path, subtitle_file=caption_file)
vertical = editor.resize(captioned.output_path, aspect_ratio="9:16")
checkpoint = editor.release_checkpoint(vertical.output_path)

print(checkpoint["thumbnail"])
print(checkpoint["storyboard"])
```

## CLI

```bash
mcp-video info interview.mp4
mcp-video trim interview.mp4 -s 00:02:15 -d 45
mcp-video video-ai-transcribe clip.mp4 --output captions.srt
mcp-video subtitles clip.mp4 captions.srt
mcp-video resize clip.mp4 --aspect-ratio 9:16
mcp-video video-quality-check clip.mp4
```

## What Agents Can Do

| Workflow | Example prompt |
| --- | --- |
| Social clips | "Turn this landscape recording into a captioned TikTok and YouTube Short." |
| Podcast production | "Find the strongest segment, trim it, normalize audio, add chapters, and export." |
| Product demos | "Create a short launch video from screenshots, title cards, and voiceover." |
| Cinematic planning | "Create a style pack and storyboard, then render shot prompts for generation." |
| Quality review | "Compare these two exports, make thumbnails, and flag visual or audio problems." |
| Batch automation | "Convert this folder of clips to web-ready MP4 with consistent loudness." |
| Code-created video | "Scaffold a Hyperframes composition, render it, then add subtitles and a watermark." |

## MCP Tools

mcp-video registers **91 MCP tools** across 11 categories, including a `search_tools` discovery tool so agents can find the right operation without loading every tool description into context.

| Category | Count | Highlights |
| --- | ---: | --- |
| Core video editing | 32 | trim, merge, resize, crop, rotate, convert, overlays, subtitles, export, cleanup, templates |
| Cinematic creation | 4 | project scaffold, style-pack parsing, storyboard parsing, shot prompt expansion |
| AI-assisted media | 11 | transcription, scene detection, upscaling, stem separation, silence removal, color grading |
| Hyperframes | 8 | init, preview, render, still, validate, compositions, add block, post-process |
| Procedural audio | 7 | synthesize, compose, presets, effects, sequences, generated audio, spatial audio |
| Visual effects | 8 | vignette, glow, noise, scanlines, chromatic aberration, luma key, mask, shape mask |
| Transitions | 3 | glitch, morph, pixelate |
| Layout and motion | 6 | grid, picture-in-picture, animated text, counters, progress bars, auto-chapters |
| Analysis | 8 | scene detection, thumbnail, preview, storyboard, quality compare, metadata, waveform, release checkpoint |
| Image analysis | 3 | extract colors, generate palettes, analyze product images |
| Discovery | 1 | `search_tools` |

```python
from mcp_video import Client

editor = Client()
matches = editor.search_tools("subtitle")
print(matches["tools"])
```

Full reference: [docs/TOOLS.md](docs/TOOLS.md)

## Agent-Safe Workflow

For autonomous agents, the intended path is inspect, edit, verify, then ask a human to review release artifacts:

```python
from mcp_video import Client

client = Client()

print(client.inspect("trim"))

result = client.pipeline(
    [
        {"op": "trim", "input": "source.mp4", "start": "00:01:00", "duration": "00:00:45"},
        {"op": "add_text", "text": "Launch clip", "position": "top-center"},
        {"op": "normalize_audio"},
        {"op": "resize", "aspect_ratio": "9:16"},
        {"op": "export", "quality": "high"},
        {"op": "release_checkpoint"},
    ],
    output_path="final-short.mp4",
)
```

Safety contract:

- Media-producing calls return structured results with output paths.
- Analysis and discovery calls return structured JSON reports.
- Tool discovery is available through `search_tools()` and `Client.inspect()`.
- Unexpected keyword errors are converted into actionable `MCPVideoError` guidance.
- Do not publish agent-generated video without `video_quality_check`, `video_release_checkpoint`, and human visual/audio inspection.

## Documentation

- [Tool reference](docs/TOOLS.md)
- [Python client reference](docs/PYTHON_CLIENT.md)
- [CLI reference](docs/CLI_REFERENCE.md)
- [AI agent discovery guide](docs/AI_AGENT_DISCOVERY.md)
- [Testing guide](docs/TESTING.md)
- [FAQ](docs/faq.md)
- [llms.txt](llms.txt)

## Testing

Run the standard development suite after installing dev dependencies:

```bash
pytest tests/ -v -m "not slow and not hyperframes"
```

See the [testing guide](docs/TESTING.md) for slower media and integration checks.

## Development

```bash
git clone https://github.com/KyaniteLabs/mcp-video.git
cd mcp-video
python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
pytest tests/ -v -m "not slow and not hyperframes"
```

## Community

- [Contributing](CONTRIBUTING.md)
- [Code of Conduct](CODE_OF_CONDUCT.md)
- [Governance](GOVERNANCE.md)
- [Maintainers](MAINTAINERS.md)
- [Security](SECURITY.md)
- [Support](SUPPORT.md)
- [Roadmap](ROADMAP.md)
- [Changelog](CHANGELOG.md)
- [GitHub Discussions](https://github.com/KyaniteLabs/mcp-video/discussions)

## License

Apache 2.0. See [LICENSE](LICENSE).

Built with [FFmpeg](https://ffmpeg.org/), [Hyperframes](https://hyperframes.io/), and the [Model Context Protocol](https://modelcontextprotocol.io/).
