Back to MCP Servers
🔌

LvcidPsyche/auto-browser

MITAPI key required

](https://glama.ai/mcp/servers/LvcidPsyche/auto-browser) 🐍 🏠 🐧 🍎 🪟 - Open-source MCP-native browser agent with human takeover via noVNC, reusable auth profiles, and approval/audit rails. Playwrig

PythonBrowser

Install

npx -y lvcidpsyche-auto-browser

Required environment variables

API_BEARER_TOKENSet in your MCP config
AUTH_STATE_ENCRYPTION_KEYSet in your MCP config

claude_desktop_config.json

claude_desktop_config.json
{
  "mcpServers": {
    "lvcidpsyche-auto-browser": {
      "command": "npx",
      "args": [
        "-y",
        "lvcidpsyche-auto-browser"
      ],
      "env": {
        "API_BEARER_TOKEN": "<YOUR_API_BEARER_TOKEN>",
        "AUTH_STATE_ENCRYPTION_KEY": "<YOUR_AUTH_STATE_ENCRYPTION_KEY>"
      }
    }
  }
}

Add this to your Claude Desktop config file. Find it at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS.

What this does

LvcidPsyche/auto-browser exposes a set of tools to Claude over the Model Context Protocol. After you add it to claude_desktop_config.json (snippet above) and restart Claude Desktop, those tools become callable inside any conversation. That makes it useful when you want Claude to reach into live web pages and browser sessions without copy-pasting context every turn.

Requirements

This server needs the following environment variables to be set before it can run:

API_BEARER_TOKEN
AUTH_STATE_ENCRYPTION_KEY

Set these via the env object in your MCP config (see claude_desktop_config.json snippet above).

Common use cases

  • Navigate, fill forms, and scrape pages on demand from Claude
  • Test UI flows or capture screenshots as part of a debugging session
  • Reach data behind logins or interactive pages that simple HTTP fetch cannot