Documentation

Add web browsing to your AI agents in 30 seconds.

Quick Start

1. Create an account and generate an API key from the dashboard.
2. Add the config below to your MCP client (Claude Desktop, Cursor, etc.).
3. Ask your agent to browse any web page.

Claude Desktop

Add this to your Claude Desktop config file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "botbrowser": {
      "url": "https://api.thebotbrowser.com/sse",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Replace YOUR_API_KEY with your key from the dashboard.

Cursor

Go to Settings → MCP Servers → Add Server and enter:

Name: BotBrowser
Type: SSE
URL:  https://api.thebotbrowser.com/sse
Headers:
  Authorization: Bearer YOUR_API_KEY

MCP Tools

Once connected, your agent has access to these tools:

REST API

For non-MCP clients, use the REST API directly:

curl -X POST https://api.thebotbrowser.com/extract \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com"}'

Request Body

{
  "url": "https://example.com",
  "format": "markdown"
}

Response

{
  "url": "https://example.com",
  "title": "Example Domain",
  "description": "...",
  "content": "# Example Domain\n\nThis domain is for...",
  "links": [
    { "text": "More information", "href": "https://www.iana.org/..." }
  ],
  "metadata": {
    "rawTokenEstimate": 1200,
    "cleanTokenEstimate": 85,
    "tokenSavingsPercent": 93,
    "wordCount": 28,
    "fetchedAt": "2026-02-27T10:00:00.000Z"
  }
}

Rate Limits

Rate limit headers are included in every response: X-RateLimit-Remaining and X-RateLimit-Reset.

Open Source Library

BotBrowser's extraction engine is open source and can be used standalone without the hosted service:

npm install botbrowser    # JavaScript / TypeScript
pip install botbrowser    # Python

import { extract } from 'botbrowser';

const result = await extract('https://example.com');
console.log(result.content);  // clean markdown

See the GitHub repo for full documentation.

Error Codes

Questions? hello@thebotbrowser.com