VidMCP
Provides subject segmentation using MediaPipe.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@VidMCPSegment the person and add a cosmic glow behind them"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Creator polish pipeline
One call for a publish-ready talk-head:
orient → denoise → BGM → captions → optional BG replace → export presetTool | What it does |
| Full recipe in one shot |
| Denoise · gate · EQ · loudnorm |
| Ambient pad under voice (ducking) |
| Whisper words + brand burn-in |
| Matte + space / blur / solid plate |
| Dead air & filler removal |
|
|
| 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 |
|
| Expose only the tools for that product path |
|
| Drop heavy keys / truncate long payloads |
|
| 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 neededRecipes: talking_head_polish · talking_head_reels · talking_head_space · talking_head_tight · talking_head_infographics.
For full surface (debug): VIDMCP_TOOL_PACK=all.
Related MCP server: media-mcp
Gallery
Sample | GIF | MP4 |
Creator polish | ||
Flow field | ||
Tesseract | ||
Behind the subject | ||
Kinetic | ||
Unit circle | ||
Pipeline |
Install
Needs: Python 3.11+, ffmpeg, uv recommended
uv tool install vidmcp
vidmcp --doctor
# or
pip install 'vidmcp[creator]' # + faster-whisper + mediapipeMCP (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-bf16Core 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_renderPrefer 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 snippetsAuthor
Dhiraj Lochib — Full-Stack, Blockchain, AI
dhirajlochib.com · GitHub · LinkedIn · dhirajch145@gmail.com
License
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/dhirajlochib/VidMcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server