Skip to content
AgentAtlas

Official server by Browserless

Browserless MCP server

Drive a cloud browser, scrape, search, crawl, export pages as PDF or screenshots, and run Lighthouse audits on Browserless.

Install

Pick your agent and copy one line. Remote servers ask you to sign in on first use.

claude mcp add --transport http browserless https://mcp.browserless.io/mcp
Full steps for Claude Code →

Comparing options? Browser automation MCP servers compared →

What it can do

From Browserless's own MCP documentation.

Sign in

OAuth with your Browserless account, or an API token in the Authorization header or a token query parameter.

Tools (14)

browserless_agentbrowserless_smartscraperbrowserless_functionbrowserless_exportbrowserless_searchbrowserless_mapbrowserless_performancebrowserless_crawlbrowserless_skillbrowserless_accountbrowserless_usagebrowserless_logsbrowserless_sessionsbrowserless_profiles

Options

  • Hosted server or local stdio and HTTP via the npm package
  • Regional endpoints
  • browserless_agent keeps a browser session across turns when keepSessionAlive is true
  • Account tools are read-only

Good to know

  • Every tool call opens a browser session that consumes Browserless units, plus proxy and CAPTCHA costs
  • Sessions are one-shot by default since server v1.33.0

Details

Registry name
io.browserless/mcp
Latest version
1.46.0 (updated 2026-11-06)
Endpoints

https://mcp.browserless.io/mcp (streamable-http)

Packages

@browserless.io/mcp (npm)

Links
Browserless docsSource

More in Browser automation

Reviewed Oct 21, 2026. Official means published under Browserless's namespace in the MCP registry. It is not a security audit.

Built an MCP server? Get it listed everywhere →

Shipping an Android app? Google Play needs 12 testers for 14 days first. Get them with Tester Exchange →