video-generation-mcp
An MCP server that makes narrated "tech explained" reels for Facebook, Instagram and YouTube Shorts: script → Gemini voice → line timings → 3D (three.js) or 2D visuals → background render → music mix → final mp4. It also makes white editorial image posts, step-by-step infographics, thumbnails, captions and other formats.
Built with FastMCP for Claude Desktop, Claude Code and any MCP client.
Tools (39)
| Area | Tools |
|---|---|
| Overview | list_reels, reel_status, studio_doctor |
| Reel + script | create_reel, write_script, check_script, write_caption_file |
| Voice | generate_voice, speak_script, speak, import_voice |
| Timing | align_voice, set_line_times |
| Code + assets | list_files, read_file, write_file, add_asset, list_templates, save_as_template |
| Look before rendering | render_stills (contact sheet image), safe_zone_check |
| Render | start_render, render_status, cancel_render, finish_reel |
| Music | set_music (calm, upbeat, tense, ambient, none), import_music |
| After rendering | preview_video, check_audio, add_captions, make_thumbnail, export_formats, trim_or_speed, compress_video |
| Image posts | render_image_post, render_infographic |
| Planning + cleanup | log_topic, list_topics, clean_reel |
A typical reel: create_reel → write_script → check_script → generate_voice → align_voice →
write_file (3d/world.js, 3d/shots.js) → render_stills → safe_zone_check → start_render → render_status →
preview_video.
Install
Requirements: Python 3.10+, uv, ffmpeg (with libass for burned captions).
cp .env.example .env # set BX_STUDIO_DIR and GEMINI_API_KEY
uv sync
uv run playwright install chromium
uv run video-generation-mcp doctor
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
"video-generation-mcp": {
"command": "uv",
"args": ["run", "--directory", "/path/to/studio-mcp", "video-generation-mcp"]
}
Configuration
| Variable | Default | Meaning |
|---|---|---|
BX_STUDIO_DIR |
required | Studio folder with reels/, posts/, templates/, topics.json |
GEMINI_API_KEY |
— | Text-to-speech key (also read from <studio>/.env) |
BX_VOICE / BX_TTS_MODEL |
Iapetus / gemini-2.5-flash-preview-tts |
Default voice and model |
BX_GL |
auto |
gpu (macOS default), swiftshader (software) |
BX_FPS / BX_WORKERS |
24 / 2 |
Render frame rate and parallel browser workers |
BX_FOOTNOTE |
Simulated · illustration |
Small footnote on 3D frames |
MCP_TRANSPORT, MCP_HOST, MCP_PORT |
stdio, 127.0.0.1, 8000 |
Server transport |
Run video-generation-mcp --read-only to expose only the tools that don't write files.
Docs
Development
uv sync
uv run pytest # 62 tests; browser/ffmpeg tests skip when those are missing
uv run ruff check src tests && uv run mypy
Metadata
Release files for video-generation-mcp 0.2.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| video_generation_mcp-0.2.1.tar.gz | 597.9 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| video_generation_mcp-0.2.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.2 MB
Release files / video_generation_mcp-0.2.1.tar.gz
| Download URL | video_generation_mcp-0.2.1.tar.gz |
|---|---|
| Size | 597.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1f80f30e3ba5014f4973bec00dbfdf490308ba5627db5bfd4f5b22d28b410b2f
|
|
BLAKE2b-256 checksum How to use checksums |
0deae61afb6b0e1d64b7bc108762c639dc943129037619a222e0ee1cb59a9e1b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.4 {"installer":{"name":"uv","version":"0.11.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / video_generation_mcp-0.2.1-py3-none-any.whl
| Download URL | video_generation_mcp-0.2.1-py3-none-any.whl |
|---|---|
| Size | 610.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b1a75d81fc01ee45f6f6eb843df305bc65581c312cd8218c29fe66b14950d14d
|
|
BLAKE2b-256 checksum How to use checksums |
eebf06f1e5e6213ddee92543763ca0bf9d2b783f599e139006991c88eee39bc4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.4 {"installer":{"name":"uv","version":"0.11.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for video-generation-mcp 0.2.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.