Browserless MCP Server
The Browserless MCP server gives AI assistants full browser automation capabilities through the Model Context Protocol. Connect Claude Desktop, Cursor, VS Code, Windsurf, or any MCP-compatible client to the hosted server and start scraping, searching, mapping, crawling, running Lighthouse audits, exporting, downloading, and running custom browser code — no infrastructure required.
Prerequisites
- A Browserless account - either an API token from your account dashboard, or OAuth sign-in
- An MCP-compatible client (Claude Desktop, Cursor, VS Code, Windsurf, etc.)
Hosted Server
Browserless provides a hosted MCP server ready to use:
https://mcp.browserless.io/mcp
No installation or environment variables required. See Authentication for how to connect.
Authentication
The hosted server supports three authentication methods:
| Method | Best for |
|---|---|
| OAuth (Browserless account login) | Clients that support OAuth — no token needed |
Authorization header | Clients that support custom headers |
token query parameter | URL-only clients (e.g. Claude.ai custom connectors) |
When multiple methods are present, they are evaluated in this order: Authorization header (plain API key) → token query parameter → OAuth JWT.
OAuth
For clients that support OAuth (for example Claude Desktop or Cursor), the hosted server can authenticate you through your Browserless account - no API token required. When you connect, your client will open a browser window to sign in. After authenticating, the server resolves your account automatically.
OAuth is enabled on the hosted server at https://mcp.browserless.io/mcp with no extra configuration needed.
API Token
Pass your API token as a Bearer header or query parameter:
- Header (recommended):
Authorization: Bearer your-token-here - Query parameter:
?token=your-token-here
Client Setup
- Claude.ai
- Claude Desktop
- Cursor
- VS Code
- Windsurf
Claude.ai supports MCP servers via custom connectors. Since the connector form only accepts a URL, pass your token as a query parameter:
- Go to Settings > Connectors in Claude.ai.
- Click Add custom connector.
- Enter a name (e.g.,
Browserless) and the following URL:
https://mcp.browserless.io/mcp?token=your-token-here
- Click Add.
Add to your claude_desktop_config.json:
{
"mcpServers": {
"browserless": {
"url": "https://mcp.browserless.io/mcp",
"headers": {
"Authorization": "Bearer your-token-here"
}
}
}
}
Add to your Cursor MCP settings:
{
"mcpServers": {
"browserless": {
"url": "https://mcp.browserless.io/mcp",
"headers": {
"Authorization": "Bearer your-token-here"
}
}
}
}
Add to your VS Code settings (settings.json):
{
"mcp": {
"servers": {
"browserless": {
"type": "http",
"url": "https://mcp.browserless.io/mcp",
"headers": {
"Authorization": "Bearer your-token-here"
}
}
}
}
}
Add to your Windsurf MCP configuration:
{
"mcpServers": {
"browserless": {
"url": "https://mcp.browserless.io/mcp",
"headers": {
"Authorization": "Bearer your-token-here"
}
}
}
}
Replace your-token-here with your Browserless API token from the account dashboard.
Clients that support OAuth can connect without a token - the server will prompt you to sign in with your Browserless account.
Regional Endpoints
By default, the hosted MCP server connects to the US West (San Francisco) Browserless region. To use a different region, pass the endpoint as a header or query parameter:
| Region | Endpoint |
|---|---|
| US West — San Francisco (default) | https://production-sfo.browserless.io |
| Europe — London | https://production-lon.browserless.io |
| Europe — Amsterdam | https://production-ams.browserless.io |
Using the x-browserless-api-url header (for clients that support headers):
{
"mcpServers": {
"browserless": {
"url": "https://mcp.browserless.io/mcp",
"headers": {
"Authorization": "Bearer your-token-here",
"x-browserless-api-url": "https://production-sfo.browserless.io"
}
}
}
}
Using the browserlessUrl query parameter (for URL-only clients like Claude.ai):
https://mcp.browserless.io/mcp?token=your-token-here&browserlessUrl=https://production-sfo.browserless.io
Tools
The MCP server exposes nine tools to your AI assistant, split across two reference pages:
Browser Agent
A single stateful tool, browserless_agent, that drives a browser session across turns. The session persists across tool calls, so the model can navigate, snapshot the page, click, type, fill forms, and react to what it sees — all within one browser context. Ideal for logins, multi-step flows, and anything that needs the browser's state to survive between turns.
REST API Tools
Eight stateless tools that wrap individual Browserless REST endpoints — one call in, one result out:
| Tool | Purpose |
|---|---|
browserless_smartscraper | Scrape any URL with cascading strategies (HTTP → proxy → headless → CAPTCHA solving) |
browserless_function | Run custom Puppeteer JavaScript on the Browserless cloud |
browserless_download | Trigger and retrieve browser-initiated file downloads |
browserless_export | Export a page as HTML, PDF, image, or full offline ZIP |
browserless_search | Web/news/image search with optional scraping of each result |
browserless_map | Discover all URLs on a site via sitemap and link extraction |
browserless_performance | Run a Lighthouse audit (accessibility, performance, SEO, PWA, best practices) |
browserless_crawl | Crawl a site from a seed URL and scrape every discovered page |
Further Reading
- Browser Agent — the stateful, multi-turn
browserless_agenttool - REST API Tools — the eight stateless MCP tools
- Browserless Account Dashboard - Get your API token
- REST APIs — Direct REST API access
- BrowserQL — GraphQL-based browser automation
- MCP Overview — Compare Browserless MCP servers
- AI Integrations — Other AI platform integrations