Browserless

Name: Browserless
Author: browserless

@browserless

代码仓库

关于 Browserless

Official MCP server for the Browserless.io

#web-automation #scraping

基本信息

分类

浏览器自动化

许可证

NOASSERTION

运行时

node

传输方式

stdio

发布者

browserless

提交者

Anderson Martínez

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "browserless": {
      "type": "http",
      "url": "https://mcp.browserless.io/mcp",
      "headers": {
        "Authorization": "Bearer your-token-here",
        "x-browserless-api-url": "https://production-sfo.browserless.io"
      }
    }
  }
}

工具

Scrape a single webpage and return its content as markdown or HTML. Handles JavaScript-heavy pages and anti-bot measures automatically. For content across multiple pages, use `browserless_crawl`; to list a site's URLs, use `browserless_map`.

Search the web using Browserless and optionally scrape each result. Supports web, news, and image search with geo-targeting and time filters.

Discover and map all URLs on a website. Scans via sitemaps and link extraction. Returns URLs with optional titles and descriptions. Useful for site audits and content discovery.

Crawl a website and scrape every discovered page. Supports depth control, path filtering, sitemap strategies, and configurable scrape options. Returns scraped content and metadata for each page.

Run Lighthouse audits on any URL. Returns scores and metrics for accessibility, best practices, performance, PWA, and SEO. Optionally filter by category or supply performance budgets.

Execute custom Puppeteer JavaScript on the Browserless cloud. The function receives a `page` object and optional `context`; return `{ data, type }` to control the payload and Content-Type.

Export a webpage via the Browserless `/export` API. Fetches the URL and returns its native content (HTML, PDF, image, etc.) with automatic content-type detection.

Drive a persistent browser session via a ReAct loop: snapshot the page, plan, batch interactions (click, type, scroll, evaluate, etc.), and re-snapshot. Uses ref-based selectors derived from snapshots, supports multi-tab workflows, screenshots, captcha solving, live URLs, and file upload/download (captured downloads auto-surface as handles; bytes never enter context).

Load an on-demand recipe for a non-trivial page mechanic (shadow DOM, cookie consent, modals, captchas, dynamic content, snapshot misses, screenshots, tabs). Companion to `browserless_agent`.

概览

What is Browserless?

Browserless is an MCP (Model Context Protocol) server that exposes the Browserless.io smart scraper API to LLM clients like Claude Desktop, Cursor, VS Code, and Windsurf. It allows AI agents to scrape, crawl, search, audit, and automate web pages directly.

How to use Browserless?

Obtain an API token from browserless.io (free tier available). Configure your MCP client with the URL https://mcp.browserless.io/mcp?token=your-token-here or use the Authorization: Bearer your-token-here header. No local installation is required; the server is hosted.

Key features of Browserless

Scrape JavaScript-heavy pages with anti-bot handling automatically.
Crawl entire websites with depth control and path filtering.
Search the web and scrape results with geo-targeting filters.
Run Lighthouse audits for accessibility, performance, and SEO.
Execute custom Puppeteer JavaScript in the cloud.
Drive persistent browser sessions via ReAct loop with skill library.

Use cases of Browserless

Scraping JavaScript-rendered content that static tools miss.
Mapping all URLs on a website for content audits.
Searching and scraping multiple results with geo-targeting.
Running Lighthouse performance audits on any URL.
Automating complex multi-tab workflows with persistent sessions.

FAQ from Browserless

How do I authenticate with the Browserless MCP server?

Use a Bearer token in the Authorization header (Authorization: Bearer your-token-here) or pass the token as a ?token= query parameter in the URL.

Can I connect to a specific regional Browserless endpoint?

Yes. Add the x-browserless-api-url header or the browserlessUrl query parameter (e.g., https://production-lon.browserless.io). Headers take precedence when both are present.

Does Browserless support residential proxies?

Yes, via the proxy object on the browserless_agent tool. Set "proxy": "residential" and optionally specify country, state, city, or sticky IP. It requires an eligible plan for some options.

What are Skills in the Browserless MCP server?

Skills are on-demand recipes for handling tricky page mechanics like shadow DOM, cookie consent dialogs, modals, captchas, dynamic content, and multi-tab workflows. They auto-inject into agent responses or can be loaded manually via the browserless_skill tool.

Do I need to install anything locally to use this MCP server?

No. The Browserless MCP server is hosted at https://mcp.browserless.io/mcp. You only need an API token and an MCP-compatible client (Claude Desktop, Cursor, VS Code, Windsurf, etc.).