Browser Automation

Browserbase MCP

Browserbase is a hosted browser infrastructure with an MCP wrapper. You don't manage browsers — they do. Stealth mode and session persistence are built in.

0% Pass ❌Key Required 🔑Tested 📅
0% (0/5 tasks)
View on GitHubby Browserbase
README badge
MCP Select Browserbase MCP benchmark badge
[![MCP Select](https://mcpselect.com/badges/browserbase-mcp.svg)](https://mcpselect.com/servers/browserbase-mcp/)

Benchmark results

Pass Rate
0%(5 tasks)
0% (0/5 tasks)
SpeedN/A
Tested OnJun 8, 20266 tools found
MetricValue
Tools discovered6 tools found
ScopeLocal only
Pricing$49/mo
Auth requirementRequires BROWSERBASE_API_KEY
Verdict5 tasks skipped. Server lacks equivalent tools

Install config

Claude Desktop (macOS)
// Requires BROWSERBASE_API_KEY env var
{"mcpServers": {"browserbase": {"command": "npx", "args": ["-y", "@browserbase/mcp@latest"], "env": {"BROWSERBASE_API_KEY": "your-key"}}}}
Cursor
// Requires BROWSERBASE_API_KEY env var
{"mcpServers": {"browserbase": {"command": "npx", "args": ["-y", "@browserbase/mcp@latest"], "env": {"BROWSERBASE_API_KEY": "your-key"}}}}
VS Code
// .vscode/mcp.json
{
  "servers": {
    "browserbase": {
      "command": "npx",
      "args": ["-y", "@browserbase/mcp@latest"],
      "env": {
        "BROWSERBASE_API_KEY": "your-key"
      }
    }
  }
}

Pros

  • +Package installs successfully

Cons

    Best for

    Teams without DevOps, stealth scraping, persistent sessions

    Related servers in Browser Automation

    Frequently asked questions

    How do I install Browserbase MCP?

    Copy the config above into your AI assistant's MCP settings file:

    • Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Cursor: Settings → MCP → Add Server
    • VS Code: .vscode/mcp.json
    Does it require an API key?

    Yes. You need to set the BROWSERBASE_API_KEY environment variable. We could not test this server without credentials, so our evaluation is based on documentation and community reports.

    How were these results measured?

    We run each server through a standardized test harness that:

    1. Installs the server via npx in a fresh environment
    2. Discovers available tools using the MCP SDK
    3. Executes real tasks (navigate, click, screenshot, etc.)
    4. Validates outputs with semantic assertions (not string matching)
    5. Measures latency percentiles and pass rate

    All test scripts are open source on GitHub.

    Related categories