VidMCP

<p align="center"> <img src="https://raw.githubusercontent.com/dhirajlochib/VidMcp/main/demos/samples/07_creator_polish.gif" width="640" alt="VidMCP 1.1 Creator polish" /> </p>

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

<p align="center"> <em>Agents don’t describe video. They cut it.</em> </p>

<p align="center"> <a href="https://vidmcp.com"><img alt="Website" src="https://img.shields.io/badge/vidmcp.com-d4ff2a?style=flat-square&labelColor=050507&color=d4ff2a" /></a> <a href="https://pypi.org/project/vidmcp/"><img alt="PyPI" src="https://img.shields.io/badge/PyPI-2affd1?style=flat-square&labelColor=050507" /></a> <a href="https://dhirajlochib.com/"><img alt="Author" src="https://img.shields.io/badge/Dhiraj%20Lochib-b18cff?style=flat-square&labelColor=050507" /></a> <img alt="Python" src="https://img.shields.io/badge/Python_3.11+-ffa24e?style=flat-square&labelColor=050507" /> <img alt="License" src="https://img.shields.io/badge/MIT-efefeb?style=flat-square&labelColor=050507" /> </p>

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

---

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

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

<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" /><br/> _{<b>Behind the subject</b>} </td> <td align="center" width="50%"> <img src="https://raw.githubusercontent.com/dhirajlochib/VidMcp/main/demos/samples/02_tesseract.gif" width="100%" alt="Tesseract" /><br/> _{<b>Tesseract</b> · 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" /><br/> _{<b>Flow field</b>} </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" /><br/> _{<b>Unit circle</b>} </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

---

Author

Dhiraj Lochib — Full-Stack, Blockchain, AI
dhirajlochib.com · GitHub · LinkedIn · dhirajch145@gmail.com

---

License

MIT