Server data from the Official MCP Registry
Video production MCP: 55 tools — edit, grade, TTS captions, beat-sync, master, AI generate.
Video production MCP: 55 tools — edit, grade, TTS captions, beat-sync, master, AI generate.
Valid MCP server (1 strong, 3 medium validity signals). No known CVEs in dependencies. Package registry verified. Imported from the Official MCP Registry.
5 files analyzed · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Set these up before or after installing:
Environment variable: VIDPROD_WORKSPACE
Environment variable: VIDPROD_INPUT
Environment variable: VIDPROD_OUTPUT
Environment variable: FAL_KEY
Environment variable: WAN2GP_PATH
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-pachote-nira-video-mcp": {
"env": {
"FAL_KEY": "your-fal-key-here",
"WAN2GP_PATH": "your-wan2gp-path-here",
"VIDPROD_INPUT": "your-vidprod-input-here",
"VIDPROD_OUTPUT": "your-vidprod-output-here",
"VIDPROD_WORKSPACE": "your-vidprod-workspace-here"
},
"args": [
"nira-video-mcp"
],
"command": "uvx"
}
}
}From the project's GitHub README.
The most complete video production MCP. Edit, grade, generate AI video, master audio, generate TTS captions, and deliver to any platform — all from a Claude conversation.
pip install nira-video-mcp
From a single Claude prompt:
"Trim clip.mp4 to 30 seconds, apply a cinematic teal-orange grade, normalize audio to -14 LUFS, add my logo in the bottom right, and export for YouTube 1080p"
"Generate a 5-second aerial shot of a neon city at night using Kling 3.0, then apply vintage film grain and export for TikTok"
"Create a project from 6 clips with crossfade transitions, add background music at 20% volume, burn in subtitles from transcript.srt, render at ProRes 4444"
| Module | Tools |
|---|---|
| Inspect | vid_inspect vid_probe vid_thumbnail vid_list_workspace vid_waveform |
| Edit | vid_trim vid_concat vid_resize vid_speed vid_filter vid_overlay vid_loop vid_reverse vid_stabilize vid_transition |
| Grade | vid_grade vid_lut vid_grain vid_vignette vid_chromakey vid_glitch vid_halation vid_motion_blur |
| Audio | aud_extract aud_replace aud_normalize aud_mix aud_add_music aud_silence aud_master aud_duck_smart aud_detect_beats vid_tts_caption |
| Motion Graphics | vid_text_overlay vid_lower_third vid_title_card vid_subtitles vid_progress_bar vid_manim_render |
| AI Generation ⭐ PRO | ai_gen_wan2gp ai_gen_fal ai_gen_status ai_gen_cancel ai_gen_list_models |
| Delivery | vid_export vid_export_hls⭐ vid_thumbnail_sprite⭐ vid_chapters vid_metadata |
| Projects | proj_create proj_list proj_render |
| Render Queue | render_status render_cancel render_list |
⭐ = PRO tier
Option 1 — pip (recommended):
pip install nira-video-mcp
Add to Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"nira-video-mcp": {
"command": "nira-video-mcp",
"env": {
"VIDPROD_OUTPUT": "/path/to/output",
"VIDPROD_INPUT": "/path/to/clips",
"FAL_KEY": "your-fal-key"
}
}
}
}
Option 2 — Claude Code:
claude mcp add nira-video-mcp nira-video-mcp \
--env VIDPROD_OUTPUT="/path/to/output" \
--env VIDPROD_INPUT="/path/to/clips"
Requirements: Python 3.11+ · FFmpeg in PATH
Generate real video clips from text or image prompts — directly from Claude:
| Model | Provider | Cost/sec | Best for |
|---|---|---|---|
| Wan2GP | Local GPU | Free | Privacy, NSFW, unlimited |
| Kling 3.0 | fal.ai | $0.084 | Best value, 5-10s clips |
| Luma Ray3 | fal.ai | $0.08 | Best image-to-video |
| Veo 3.1 | fal.ai | $0.40 | Highest quality + audio |
| MiniMax Hailuo 2.3 | fal.ai | $0.015 | Cheapest, high volume |
| Pika 2.2 | fal.ai | $0.05 | Fast loops from image |
> "Generate a 5-second slow motion shot of waves crashing on rocks,
cinematic, golden hour lighting, using Kling 3.0"
Unlock AI generation: NIRA Video MCP PRO — $49 one-time →
8 built-in cinematic looks:
| Look | Description |
|---|---|
teal_orange | Hollywood blockbuster — teal shadows, warm highlights |
vintage_film | Faded film stock with lifted blacks |
noir | High-contrast black and white |
golden_hour | Warm amber summer light |
cold_blue | Desaturated thriller/crime aesthetic |
blockbuster | Vibrant, punchy streaming look |
sunset_warm | Rich oranges and deep shadows |
moody_green | Matrix/Fincher desaturated green tint |
Plus: custom .cube LUT support, VHS/glitch, film halation, chromakey, motion blur.
15 platform presets with correct specs for every major platform:
youtube_4k youtube_1080 youtube_shorts tiktok instagram_reels instagram_feed twitter facebook linkedin prores_4444 prores_422 h265_4k av1_web gif web_mp4
| Variable | Default | Description |
|---|---|---|
VIDPROD_OUTPUT | ~/video_output | Output directory |
VIDPROD_INPUT | ~/video_input | Input clips directory |
VIDPROD_WORKSPACE | ~/video_workspace | Projects directory |
FAL_KEY | — | fal.ai key for cloud AI gen |
WAN2GP_PATH | D:/Wan2GP | Wan2GP install path |
NIRA_PRO_KEY | — | PRO license key |
Get NIRA Video MCP PRO — $49 one-time
PRO unlocks:
vid_export_hls)vid_thumbnail_sprite)Set your key:
export NIRA_PRO_KEY=your-license-key
Or in claude_desktop_config.json:
"NIRA_PRO_KEY": "your-license-key"
MIT — free to use, modify, redistribute. PRO features require a license key.
Built with FastMCP · Powered by FFmpeg · AI generation via fal.ai and Wan2GP
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.