# BrowsingBee

> BrowsingBee is a freemium MCP server for browser automation. Hosted browser MCP connector that opens pages, searches the web and reads PDFs for Claude. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** Web, API
- **Website:** https://www.browsingbee.com
- **MCP Registry name:** io.github.theindianappguy/browsingbee-mcp
- **Categories:** browser automation, web search and scraping
- **Listing updated:** 2026-11-17

## About

BrowsingBee runs a real Chrome on its own servers, so an assistant on a phone or the web can read pages without anything installed locally. JavaScript-rendered sites work, and results come back as readable text rather than raw HTML.

Seven read-only tools cover the job: open_page, search_web, screenshot_page (first screen or full page, desktop or phone width), extract_data for prices, specs, tables or contacts, read_pdf for up to 50 pages, get_links, and a free usage check. A page load is one tool call that renders, searches or reads something.

Limits are stated plainly. It does not log in, fill forms or buy anything, cannot open pages behind a login, paywall or CAPTCHA, and cannot reach private networks. It respects robots.txt and identifies itself. Only a host name and a count are logged, and screenshots expire after 24 hours. The free plan allows 300 page loads a month at 20 a minute; Pro is rolling out on request.

## Features

- **Real-browser rendering:** Opens public pages in Chrome so JavaScript-heavy sites return readable Markdown.
- **Web search:** search_web returns titles, addresses and snippets.
- **Screenshots:** screenshot_page captures a PNG at desktop or phone width.
- **Data extraction:** extract_data shapes content for prices, specs, tables or contacts.
- **PDF reading:** read_pdf returns the text of public PDFs, up to 50 pages.
- **Read-only by design:** It will not log in, fill forms or get past CAPTCHAs.

## Good for

- Summarise a web page from the Claude phone app
- Compare two product pages without opening them
- Read a PDF link and pull out deadlines
- Find the right sub-page on a site by listing its links

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http browsingbee-mcp https://www.browsingbee.com/mcp
```

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

```sh
https://www.browsingbee.com/mcp
```

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

```json
{
  "mcpServers": {
    "browsingbee-mcp": {
      "url": "https://www.browsingbee.com/mcp"
    }
  }
}
```

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

```json
{
  "servers": {
    "browsingbee-mcp": {
      "type": "http",
      "url": "https://www.browsingbee.com/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "browsingbee-mcp": {
      "serverUrl": "https://www.browsingbee.com/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "browsingbee-mcp": {
      "type": "http",
      "url": "https://www.browsingbee.com/mcp"
    }
  }
}
```

## Tools

- `open_page`: Open a page in a real browser and return readable text as Markdown with links
- `search_web`: Search the web and return titles, addresses and snippets
- `screenshot_page`: Capture a PNG of a page, first screen or full page
- `extract_data`: Shape page content for pulling out prices, specs, tables or contacts
- `read_pdf`: Return the text of a public PDF page by page, up to 50 pages
- `get_links`: List links on a page, optionally filtered
- `usage`: Show plan, page loads used and reset date

## FAQ

### How many pages are free?

The site says 300 page loads a month, at 20 a minute.

### Can it log in or bypass CAPTCHAs?

No. It does not log in, fill forms or open pages behind logins, paywalls or CAPTCHAs.

### What is kept?

Only a host name and a count are logged, and screenshots expire after 24 hours.

### Does it work with ChatGPT?

Yes, the same connector works there, with separate setup steps.

### Is BrowsingBee free?

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

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

Run this command in your terminal: claude mcp add --transport http browsingbee-mcp https://www.browsingbee.com/mcp

### What are the best alternatives to BrowsingBee?

The closest alternatives to BrowsingBee 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/browsingbee
