# Browserless

> Browserless is a freemium MCP server for browser automation. Give an assistant a cloud browser to scrape, search, crawl and audit pages. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** Web, API, CLI
- **Website:** https://docs.browserless.io/mcp/browserless-mcp-server/setup
- **Repository:** https://github.com/browserless/browserless-mcp
- **MCP Registry name:** io.browserless/mcp
- **Categories:** browser automation, web search and scraping
- **Listing updated:** 2026-11-14

## About

The hosted endpoint at mcp.browserless.io needs no local setup and offers two sign-in styles: OAuth through your Browserless account, or an API token sent as a bearer header or a token query parameter for clients that only accept a URL.

Tools in the README include a smart scraper that returns markdown, HTML or AI-extracted JSON while handling JavaScript-heavy pages and anti-bot measures, plus crawl, map, search and performance tools. The registry entry also mentions screenshots and PDFs.

The npm package runs the same service over stdio and can point at a regional or self-hosted API URL. Setup pages cover Claude, ChatGPT, Cursor, VS Code and other clients.

## Features

- **Smart scraper:** Returns page content as markdown, HTML or extracted JSON.
- **Site crawling:** Collects content across multiple pages.
- **URL mapping:** Lists the URLs on a site.
- **Search and performance tools:** Search the web and run a performance audit.
- **OAuth or token:** Choose sign-in or an API token.

## Good for

- Scrape a JavaScript-heavy page into markdown
- Crawl a documentation site for an agent
- Audit page performance from chat
- Capture screenshots or PDFs of pages

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http mcp https://mcp.browserless.io/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.browserless.io/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.browserless.io/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.browserless.io/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://mcp.browserless.io/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.browserless.io/mcp"
    }
  }
}
```

## Tools

- `browserless_smartscraper`: Scrapes one page and returns markdown, HTML, JSON or a summary.
- `browserless_crawl`: Collects content across multiple pages.
- `browserless_map`: Lists a site's URLs.
- `browserless_search`: Searches the web.
- `browserless_performance`: Runs a performance audit of a page.

## FAQ

### Do I need an account?

Yes, a Browserless account via OAuth, or an API token.

### Can I use a token in a URL?

Yes, as a token query parameter for URL-only clients, though the bearer header is recommended.

### Can it be self-hosted?

The stdio package accepts a BROWSERLESS_API_URL for regional or self-hosted endpoints.

### Is there a free tier?

The README says a free tier is available.

### Is Browserless free?

Browserless has a free plan, with paid plans for more usage or features.

### How do I add Browserless to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://mcp.browserless.io/mcp

### What are the best alternatives to Browserless?

The closest alternatives to Browserless are Browser Use, Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search and Oya Browser.

## Alternatives

- [Browser Use](https://ai-powered.com/mcp/browser-use): Browser Use is a freemium MCP server for browser automation.
- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [Oya Browser](https://ai-powered.com/mcp/oya-browser): Oya Browser is a freemium MCP server for browser automation.
- [Mantis](https://ai-powered.com/mcp/mantis-2): Mantis is an open-source MCP server for browser automation.
- [NeuralVerge](https://ai-powered.com/mcp/neuralverge): NeuralVerge is an MCP server for web search and scraping.
- [AI-Powered directory](https://ai-powered.com/mcp/ai-powered-directory): AI-Powered directory is a free MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/browserless
