shotbox

Eyes, ears and hands for AI agents on GUI programs: a sealed X11 or Wayland session where an agent (over MCP), a script or CI reads the accessibility tree, takes screenshots, records video and sound, clicks, types and drives gamepads, then checks contrast, Tab order, visual diffs, flicker, input latency and audio dropouts. CLI, Python, Playwright.

Installation

MCP client config (paste into mcp.json)

{
  "mcpServers": {
    "shotbox": {
      "command": "npx",
      "args": [
        "shotbox"
      ]
    }
  }
}

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://github.com/mishan/shotbox

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "shotbox": {
      "command": "npx",
      "args": [
        "shotbox"
      ]
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

GitHub

Related servers