llm-video-mcp

shkyyy18/llm-video-mcp

★ 0 stars Python AI/LLM Updated today

MCP server that lets any coding agent watch videos within a token budget — scene-aware ffmpeg frames, whisper transcription, shot timeline

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

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

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "llm-video-mcp": {
      "command": "uvx",
      "args": [
        "llm-video-mcp"
      ]
    }
  }
}

Or install with pip: pip install llm-video-mcp

README Excerpt

**Let any coding agent (Claude Code / Cursor / Kimi Code …) actually *watch* a video — within a token budget.** An MCP server that downloads or ingests a video, extracts scene-aware frames with ffmpeg, transcribes speech with faster-whisper (VAD-gated), builds a shot timeline, and reverse-derives all extraction parameters from your token budget.

Topics

claude-codecoding-agentffmpegllmmcp-servervideo-analysiswhisper

llm-video-mcp

Quick Install

README Excerpt

Topics

Related AI/LLM Servers