Automate Google search

Navigate to Google, submit a search query, and extract result titles and links.

Prerequisites

• A Browserless API token from your account dashboard

Steps

AI Agent

Use the Browserless MCP server to automate a Google search from any MCP-compatible AI agent (Claude Desktop, Cursor, Windsurf, ChatGPT, etc.).

1. Connect the MCP server

Send this prompt to your AI agent to install the Browserless MCP server:

Go to https://github.com/browserless/browserless-mcp/blob/main/install.md
and follow the instructions to install the Browserless MCP server
for my client.

2. Search the web

Use browserless_search. The task starts with a search query rather than a known URL.

Use the browserless_search tool to search Google for
"best headless browser API" and return the top results

REST API

Send the BQL mutation over HTTP to the stealth endpoint. Google's bot detection blocks the /scrape endpoint, so use /stealth/bql instead.

cURL

1. Send the request

curl -X POST \
  "https://production-sfo.browserless.io/stealth/bql?token=YOUR_API_TOKEN_HERE" \
  -H "Content-Type: application/json" \
  -d "{\"query\": \"mutation GoogleSearch { goto(url: \\\"https://www.google.com/search?q=Browserless+headless+browser\\\") { status } results: mapSelector(selector: \\\"h3\\\", wait: true) { innerText } }\", \"variables\": {}}"

2. Check the output

{
  "data": {
    "goto": { "status": 200 },
    "results": [
      { "innerText": "Browserless | Headless Browser Automation & Scraping" },
      { "innerText": "Getting Started | Browserless" }
    ]
  }
}

JavaScript

1. Send the request

const query = `
  mutation GoogleSearch {
    goto(url: "https://www.google.com/search?q=Browserless+headless+browser") {
      status
    }
    results: mapSelector(selector: "h3", wait: true) {
      innerText
    }
  }
`;

const response = await fetch(
  'https://production-sfo.browserless.io/stealth/bql?token=YOUR_API_TOKEN_HERE',
  {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({ query, variables: {} }),
  }
);

const result = await response.json();
console.log(result.data.results);

2. Check the output

{
  "data": {
    "goto": { "status": 200 },
    "results": [
      { "innerText": "Browserless | Headless Browser Automation & Scraping" },
      { "innerText": "Getting Started | Browserless" }
    ]
  }
}

Python

1. Install dependencies

pip install requests

2. Send the request

import requests

query = """
  mutation GoogleSearch {
    goto(url: "https://www.google.com/search?q=Browserless+headless+browser") {
      status
    }
    results: mapSelector(selector: "h3", wait: true) {
      innerText
    }
  }
"""

response = requests.post(
    'https://production-sfo.browserless.io/stealth/bql?token=YOUR_API_TOKEN_HERE',
    json={'query': query, 'variables': {}},
)

print(response.json())

3. Check the output

{
  "data": {
    "goto": { "status": 200 },
    "results": [
      { "innerText": "Browserless | Headless Browser Automation & Scraping" },
      { "innerText": "Getting Started | Browserless" }
    ]
  }
}

Java

1. Send the request

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

String endpoint = "https://production-sfo.browserless.io/stealth/bql?token=YOUR_API_TOKEN_HERE";

String mutation = "mutation GoogleSearch { goto(url: \\\"https://www.google.com/search?q=Browserless+headless+browser\\\") { status } results: mapSelector(selector: \\\"h3\\\", wait: true) { innerText } }";
String payload = "{\"query\": \"" + mutation + "\", \"variables\": {}}";

HttpClient client = HttpClient.newHttpClient();
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create(endpoint))
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString(payload))
    .build();

HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

2. Check the output

{
  "data": {
    "goto": { "status": 200 },
    "results": [
      { "innerText": "Browserless | Headless Browser Automation & Scraping" },
      { "innerText": "Getting Started | Browserless" }
    ]
  }
}

C#

1. Send the request

using System.Net.Http;
using System.Text;
using System.Text.Json;

string endpoint = "https://production-sfo.browserless.io/stealth/bql?token=YOUR_API_TOKEN_HERE";

string mutation = "mutation GoogleSearch { goto(url: \"https://www.google.com/search?q=Browserless+headless+browser\") { status } results: mapSelector(selector: \"h3\", wait: true) { innerText } }";

var payload = new { query = mutation, variables = new { } };

using HttpClient httpClient = new HttpClient();
var jsonPayload = JsonSerializer.Serialize(payload);
var content = new StringContent(jsonPayload, Encoding.UTF8, "application/json");
var response = await httpClient.PostAsync(endpoint, content);
string responseBody = await response.Content.ReadAsStringAsync();
Console.WriteLine(responseBody);

2. Check the output

{
  "data": {
    "goto": { "status": 200 },
    "results": [
      { "innerText": "Browserless | Headless Browser Automation & Scraping" },
      { "innerText": "Getting Started | Browserless" }
    ]
  }
}

Frameworks

Use a browser connection to navigate to Google and extract results from the rendered DOM.

Puppeteer

View Full Code on GitHub

1. Install dependencies

npm install puppeteer-core

2. Connect and search

import puppeteer from 'puppeteer-core';

const browser = await puppeteer.connect({
  browserWSEndpoint: 'wss://production-sfo.browserless.io?token=YOUR_API_TOKEN_HERE',
});

try {
  const page = await browser.newPage();
  await page.goto('https://www.google.com', { waitUntil: 'networkidle2' });

  await page.type('textarea[name="q"]', 'Browserless headless browser');
  await page.keyboard.press('Enter');
  await page.waitForSelector('#search');

  const results = await page.evaluate(() =>
    Array.from(document.querySelectorAll('h3')).map((h) => ({
      title: h.innerText,
      url: h.closest('a')?.href ?? null,
    }))
  );

  console.log(results);
} finally {
  // Always close to release the session even on error.
  await browser.close();
}

3. Check the output

Run with node search.mjs. Each object in the array has a title and url.

Playwright

View Full Code on GitHub

1. Install dependencies

npm install playwright-core

2. Connect and search

import { chromium } from 'playwright-core';

const browser = await chromium.connect(
  'wss://production-sfo.browserless.io/chromium/playwright?token=YOUR_API_TOKEN_HERE'
);

try {
  const page = await browser.newPage();
  await page.goto('https://www.google.com', { waitUntil: 'networkidle' });

  await page.fill('textarea[name="q"]', 'Browserless headless browser');
  await page.keyboard.press('Enter');
  await page.waitForSelector('#search');

  const results = await page.evaluate(() =>
    Array.from(document.querySelectorAll('h3')).map((h) => ({
      title: h.innerText,
      url: h.closest('a')?.href ?? null,
    }))
  );

  console.log(results);
} finally {
  // Always close to release the session even on error.
  await browser.close();
}

3. Check the output

Run with node search.mjs. Each object in the array has a title and url.

BAP

1. Install dependencies

npm install @browserless.io/bap-ts

2. Connect and search

import Browserless from '@browserless.io/bap-ts';

const browser = Browserless.connect({
  browserWSEndpoint: 'wss://production-sfo.browserless.io/chromium/bql',
  token: 'YOUR_API_TOKEN_HERE',
});

try {
  const page = await browser.newPage();

  // BAP has no keyboard API, so navigate straight to the results URL.
  await page.goto('https://www.google.com/search?q=Browserless+headless+browser');

  // `wait: true` holds until the selector appears, so no separate wait call.
  const results = await page.mapSelector('h3', { wait: true });
  console.log(results.map((result) => result.innerText));
} finally {
  // Always close to release the session even on error.
  await browser.close();
}

3. Check the output

Run with node search.mjs. Each result carries the heading text from the search page.

BQL

View Full Code on GitHub

1. Write the mutation

Pass the query in the URL to skip typing, then use mapSelector to extract all result headings:

mutation GoogleSearch {
  goto(url: "https://www.google.com/search?q=Browserless+headless+browser") {
    status
  }
  results: mapSelector(selector: "h3", wait: true) {
    innerText
  }
}

2. Run it

Paste into the BQL IDE and click Run.

3. Check the output

{
  "data": {
    "goto": { "status": 200 },
    "results": [
      { "innerText": "Browserless | Headless Browser Automation & Scraping" },
      { "innerText": "Getting Started | Browserless" }
    ]
  }
}

Next steps

Scrape Structured Data

extract more complex data with CSS selectors

Extract Content from a URL

retrieve the full rendered HTML of any page