# BrowserSolver

> BrowserSolver is an MCP server for web search and scraping. Anti-bot-aware scraping: crawl, render, screenshot and unlock pages via one API. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Free trial
- **Platforms:** API, CLI
- **Website:** https://www.browsersolver.com
- **Repository:** https://github.com/browsersolver/browsersolver-mcp
- **MCP Registry name:** com.browsersolver/mcp
- **Categories:** web search and scraping, browser automation
- **Listing updated:** 2026-11-14

## About

The service sells scraping lanes of different weight, and the MCP tools map to them. A crawler lane pulls raw HTML with no browser, a rendering lane waits for client-side scripts to finish, and an antibot scan names the bot-protection vendor in front of a URL so you can choose a lane before spending credits. The site also lists screenshot (PNG, WebP, PDF), a WebUnlocker for Cloudflare, DataDome and Akamai on allowlisted domains, and technology detection.

Pricing is credit-based, billed on successful scrapes: crawler from $1.88 per 1,000 results, rendering from $3.76 and unlock from $5.64, with paid plans of 18,000, 40,000 and 110,000 credits and 7 to 15 requests per second. Signup gives 500 credits with no card.

A hosted endpoint at mcp.browsersolver.com takes an `x-api-key` header, or run `@browsersolver/mcp` locally over stdio.

## Features

- **Antibot detection:** Identifies which vendor protects a URL before you pick a lane.
- **Cheap HTML fetch:** Crawler lane for pages that need no JavaScript.
- **Rendered HTML:** Managed browser sessions with selector waits and load delays.
- **Unlock lanes:** WAF unlock for allowlisted domains behind Cloudflare, DataDome or Akamai.
- **Hosted or local:** Remote Streamable HTTP or local stdio, plus Docker and a .mcpb bundle.

## Good for

- Scrape retail pages that sit behind a bot wall
- Choose a scraping tier by detecting the protection vendor
- Collect rendered HTML from single-page apps
- Check credit balance from an agent

## Install

### Claude Code (Terminal)

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

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

```sh
https://mcp.browsersolver.com/
```

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

```json
{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.browsersolver.com/"
    }
  }
}
```

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

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

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

```json
{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://mcp.browsersolver.com/"
    }
  }
}
```

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

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

## Tools

- `website_antibot`: Name the bot-protection vendor in front of a URL.
- `website_crawler`: Fast HTTP pull of public HTML with no browser.
- `website_rendering`: Collect HTML after client-side scripts finish.
- `usage`: Usage statistics and credit balance.
- `stats`: Infrastructure health for an engine or endpoint; enabled per account.

## FAQ

### What do I need to start?

A BrowserSolver API key; signup includes 500 credits with no card.

### Do failed scrapes cost credits?

The pricing page says billing follows successful scrapes, not failed attempts.

### How do I authenticate the hosted server?

Send the key in the x-api-key header.

### Which tools are exposed?

website_antibot, website_crawler, website_rendering, usage and an account-enabled stats tool.

### Is BrowserSolver free?

BrowserSolver is a paid product with a free trial.

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

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

### What are the best alternatives to BrowserSolver?

The closest alternatives to BrowserSolver 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/browsersolver
