MCP 服务器

VidMCP

MCP server for video editing with text-prompt subject segmentation and compositing effects behind subjects. Enables agent-driven video creation and education animations.

README

<h1 align="center">VidMCP</h1>

Agents don’t describe video. They cut it.

MCP server for agent video editing — mattes · behind-the-subject VFX · audio polish · captions · export Built by <a href="https://dhirajlochib.com/">Dhiraj Lochib</a> · <a href="https://vidmcp.com">vidmcp.com</a> · <code>uv tool install vidmcp</code>

Creator polish pipeline

One call for a publish-ready talk-head:

orient → denoise → BGM → captions → optional BG replace → export preset

Tool	What it does
`run_talking_head_polish`	Full recipe in one shot
`process_audio`	Denoise · gate · EQ · loudnorm
`mix_bgm`	Ambient pad under voice (ducking)
`transcribe_and_caption`	Whisper words + brand burn-in
`replace_background`	Matte + space / blur / solid plate
`smart_cut_hesitations`	Dead air & filler removal
`export_render`	`youtube_16x9` · `reels_9x16` · `square_1x1`
`import_video`	Bakes portrait rotation upright by default

from vidmcp.tools.creator import run_talking_head_polish

print(run_talking_head_polish(
    "talk.mov",
    preset="reels_9x16",
    bg_mode="space",   # none | space | blur | solid
    strength=0.75,
    bgm_volume=0.35,
))

MCP agents can also call apply_recipe(..., recipe_name="talking_head_polish") or free-text run_intent(...).

Agent context (tool packs + compact results)

Agents drown when MCP hosts load ~90 tool schemas and fat JSON. VidMCP defaults to a small surface:

Setting	Default	Purpose
`VIDMCP_TOOL_PACK`	`talking_head`	Expose only the tools for that product path
`VIDMCP_COMPACT`	`1`	Drop heavy keys / truncate long payloads
`VIDMCP_MAX_RESULT_CHARS`	`4000`	Hard cap on serialized tool results

Packs: talking_head · education · vfx · admin · all

run_intent("polish talk head for reels, space bg, cut fillers", video_path="talk.mov")
project_brief(project_id)          # prefer over full get_project
list_tool_packs() / set_tool_pack("vfx")
get_project(id, detail=true)       # full manifest only when needed

Recipes: talking_head_polish · talking_head_reels · talking_head_space · talking_head_tight · talking_head_infographics.

For full surface (debug): VIDMCP_TOOL_PACK=all.

Gallery

<img src="https://raw.githubusercontent.com/dhirajlochib/VidMcp/main/demos/samples/07_creator_polish.gif" width="560" alt="Creator 1.1" /> 1.1 Creator polish — orient · denoise · BGM · captions · export

<table> <tr> <td align="center" width="50%"> <img src="https://raw.githubusercontent.com/dhirajlochib/VidMcp/main/demos/samples/03_behind_subject.gif" width="100%" alt="Behind subject" /> Behind the subject </td> <td align="center" width="50%"> <img src="https://raw.githubusercontent.com/dhirajlochib/VidMcp/main/demos/samples/02_tesseract.gif" width="100%" alt="Tesseract" /> Tesseract · 4D trails </td> </tr> <tr> <td align="center" width="50%"> <img src="https://raw.githubusercontent.com/dhirajlochib/VidMcp/main/demos/samples/01_flowfield.gif" width="100%" alt="Flow" /> Flow field </td> <td align="center" width="50%"> <img src="https://raw.githubusercontent.com/dhirajlochib/VidMcp/main/demos/samples/05_unit_circle.gif" width="100%" alt="Unit circle" /> Unit circle </td> </tr> </table>

Sample	GIF	MP4
Creator polish	gif	mp4
Flow field	gif	mp4
Tesseract	gif	mp4
Behind the subject	gif	mp4
Kinetic	gif	mp4
Unit circle	gif	mp4
Pipeline	gif	mp4

Install

Needs: Python 3.11+, ffmpeg, uv recommended

uv tool install vidmcp
vidmcp --doctor

# or
pip install 'vidmcp[creator]'   # + faster-whisper + mediapipe

MCP (Grok / Claude / Cursor)

# Grok
grok mcp add vidmcp \
  -e VIDMCP_SAM_BACKEND=mock \
  -e VIDMCP_WORKSPACE_ROOT=$HOME/vidmcp-workspaces \
  -e VIDMCP_TOOL_PACK=talking_head \
  -e VIDMCP_COMPACT=1 \
  -- uvx vidmcp

{
  "mcpServers": {
    "vidmcp": {
      "command": "uvx",
      "args": ["vidmcp"],
      "env": {
        "VIDMCP_SAM_BACKEND": "mock",
        "VIDMCP_WORKSPACE_ROOT": "/path/to/workspaces",
        "VIDMCP_TOOL_PACK": "talking_head",
        "VIDMCP_COMPACT": "1"
      }
    }
  }
}

Optional real matte on Apple Silicon:

pip install 'vidmcp[mlx]'
export VIDMCP_SAM_BACKEND=mlx
export VIDMCP_MLX_MODEL_ID=mlx-community/sam3.1-bf16

Core product


Segment	Text-prompt subject matte (SAM / MLX / MediaPipe / mock)
Compose	Effects behind the subject
Audio	Denoise, enhance, BGM duck, loudnorm
Captions	Whisper timeline + brand burn-in
Educate	Math plates + speech-locked scenes
Export	16:9 · 9:16 · 1:1 without stretch

create_project → import_video (orient)
  → process_audio → mix_bgm
  → segment_subject | replace_background
  → transcribe_and_caption → export_render

Prefer high-level paths: run_talking_head_polish · apply_recipe · run_quality_gated_pipeline.

Project layout

src/vidmcp/     MCP server, creator tools, perception, effects
demos/samples/  GIFs · MP4s for README & site
site/           vidmcp.com (static Hostinger)
configs/        Claude / Cursor snippets