videopilot

mbahgatTech/videopilot
★ 0 stars Python 🤖 AI/LLM Updated 4d ago
Agent-driven video creation toolkit: neural TTS voiceover, highlight cutting, timeline composition, NLE export. Includes a stdio MCP server (videopilot-mcp) launchable via uvx.
View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "videopilot": {
      "command": "uvx",
      "args": [
        "videopilot"
      ]
    }
  }
}

Or install with pip: pip install videopilot

README Excerpt

> Agent-driven video creation toolkit. An **MCP server** giving LLMs 20 tools > to author voiceover, cut highlights, compose timelines, and render finished > MP4s — plus a CLI for manual / scripted runs when you don't want an agent > in the loop. `videopilot` is an **MCP (Model Context Protocol) server** that lets a calling

Tools (20)

AZURE_SPEECH_KEYAZURE_SPEECH_REGIONPATHadd_slideadd_vo_segmentcomposecutdoctorexportimport_sourceinitis_up_to_datelist_projectsmbahgatTechpreview_slideproject_statusread_stateschemaset_compose_outputsilence