browser — Claude Code MCP server: what it does, how to install
This MCP server lets an AI agent use a real browser session to load authenticated pages, handle forms, and work with JavaScript-heavy sites.
claude mcp add browser -- npx -y mcpbrowserWhat browser does
browser connects an AI agent to Chrome, Edge, or Brave through MCP. It can load pages, click elements, enter values into several form fields, read the current HTML, scroll, and capture screenshots. Because it uses your browser session, the agent can work with SSO, CAPTCHA checks, redirects, and pages that need JavaScript.
The server runs on Puppeteer while presenting the agent with structured results: cleaned HTML, SPA detection, and guidance for the next action. Tabs can be reused by domain, and the DOM can be read again without loading the page from scratch.
You need Chrome, Edge, or Brave plus Node.js 18+. Without Node.js 18+, the MCP server will not start.
What it helps with
- open pages that require authentication
- handle SSO and redirect flows
- fill multi-step web forms
- read content from SPA pages
- inspect sites that require JavaScript
Example prompts for the agent
- Open the sign-in page, complete authentication, and show me the contents of the account area.
- Find the form on the current page, fill it with values from
order.json, and submit it. - Browse the site, collect the requested page data, and save the result to
report.json.
How to install browser
Platform CLI
claude mcp add browser -- npx -y mcpbrowserPlatform CLI
codex mcp add browser -- npx -y mcpbrowserConfig file
{
"mcpServers": {
"browser": {
"command": "npx",
"args": [
"-y",
"mcpbrowser"
]
}
}
}Config file
{
"servers": {
"browser": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcpbrowser"
]
}
}
}Platform CLI
gemini mcp add browser npx -y mcpbrowserStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about browser
How do I install browser in Claude Code?
Run claude mcp add browser -- npx -y mcpbrowser.
What does browser do?
It gives an AI agent access to a real browser session. The agent can load pages, deal with authentication, click controls, fill forms, and extract page content.
What does browser require?
You need Chrome, Edge, or Brave, along with Node.js 18+.
