phantom-canvas

Your Gemini web app as a service — turn the free Gemini web interface into a programmable HTTP API for image and video generation via Chrome CDP.

Browser Automation

Install Command

npx -y phantom-canvas

Claude Desktop Config

{
  "mcpServers": {
    "phantom-canvas": {
      "command": "npx",
      "args": [
        "-y",
        "phantom-canvas"
      ]
    }
  }
}

phantom-canvas is a community MCP server that connects AI assistants like Claude to your gemini web app as a service — turn the free gemini web interface into a programmable http api for image and video generation via chrome cdp. It runs locally on your machine, keeping your data private and giving you full control over the connection. Adding it to your setup expands what Claude can do without any extra coding.

About phantom-canvas

Overview

Your Gemini web app as a service — turn the free Gemini web interface into a programmable HTTP API for image and video generation via Chrome CDP.

Topics

agent-skills, mcp-server, gemini, image-generation, video-generation, browser-automation, pixel-art, game-assets, ai-agent, phantom-canvas, chrome-cdp

Who Should Use phantom-canvas?

1Analyse and describe images as part of your AI workflow
2Control a browser and scrape the web through Claude
3Extend Claude and other AI assistants with new capabilities
4Automate tasks that previously required manual steps

How to Install phantom-canvas

Before you start

You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.

1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
2Paste the install command above and press Enter — Node.js will download and run the server automatically.
3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.

The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.