Frame Lens for VS Code

io.github.makkov-design/framelens

Eyes and ears for AI agents: measured cuts, easing, palette, beats and transcripts from any video.

client:VS Code transport:stdio runtime:npm

Install Frame Lens in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "gemini-api-key",
      "description": "GEMINI_API_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "gemini-model-name",
      "description": "GEMINI_MODEL_NAME",
      "password": true
    },
    {
      "type": "promptString",
      "id": "framelens-workspace",
      "description": "FRAMELENS_WORKSPACE",
      "password": true
    },
    {
      "type": "promptString",
      "id": "framelens-auto-install",
      "description": "FRAMELENS_AUTO_INSTALL",
      "password": true
    }
  ],
  "servers": {
    "framelens": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "framelens"
      ],
      "env": {
        "GEMINI_API_KEY": "${input:gemini-api-key}",
        "GEMINI_MODEL_NAME": "${input:gemini-model-name}",
        "FRAMELENS_WORKSPACE": "${input:framelens-workspace}",
        "FRAMELENS_AUTO_INSTALL": "${input:framelens-auto-install}"
      }
    }
  }
}

VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs

Frame Lens in other clients

Frame Lens MCP server