Spiral gives your agent every tool with one account. Browse the tools →

Claude Code · Web

How to Use Google search results in Claude Code

Get Google search results with a URL, title, and description for each returned link. Use it to find relevant pages for research, compare competing content, or build a reading list before reviewing the original sources.

Prompts to try with Google search results in Claude Code

Copy an example into Claude Code, or ask in your own words.

Read package.json, then use Google search results to search site:nextjs.org/docs for the Next.js features this project uses. Save a reading list with each result's title, URL, and description.

Google search resultsClaude Code
Try asking
  • Use Google search results to search site:docs.python.org asyncio TaskGroup. Add the returned titles, URLs, and descriptions to docs/async-research.md.

  • Inspect our database migration files, then use Google search results to search site:postgresql.org/docs for CREATE INDEX CONCURRENTLY. List the returned links relevant to the migration.

  • Use Google search results to search site:react.dev "useEffect". Create a small table of returned titles, URLs, and descriptions for our React documentation review.

  • Use Google search results to search "OpenTelemetry" Node.js tracing. Save the returned links and descriptions in a research file, with repeated URLs removed.

How to set up Google search results in Claude Code

Pick the way that suits you. Each takes about two minutes.

Use Spiral's MCP server

  1. Add the hosted server

    This adds Spiral to the current project. Add --scope user to use it in every project.

    claude mcp add --transport http spiral https://api.spiral.ai/mcp
  2. Sign in

    Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.

Use the Spiral skill

  1. Send Claude Code this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. Install and sign in

    Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run Google search results

    One request; the result comes back by polling or a webhook.

    curl https://api.spiral.ai/v1/runs \
      -H "Authorization: Bearer $SPIRAL_API_KEY" \
      -H "Content-Type: application/json" \
      -H "Idempotency-Key: $(uuidgen)" \
      -d '{
        "provider": "scrapecreators",
        "model": "scrapecreators/google-search",
        "input": {
          "query": "news"
        }
      }'

Then paste one of the prompts above: Claude Code finds Google search results on Spiral, shows the price and runs it.

Google search results providers and prices

Spiral runs Google search results through ScrapeCreators. Open a card for today's price, with every fee included.

ScrapeCreatorsWeb
Google · Search
scrapecreators/google-search

Settings you can ask for

Ask Claude Code for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Pagea number

Page number to retrieve. Must be between 1 and 11; page 12 or greater returns a 400 response.

Date postedlast-hour, last-day, last-week, last-month, or last-year

Date posted

Every API field of Google · Search is on its tool page: open its card above.

What can you do with Google search results in Claude Code?

Build a reading list of official documentation for the dependencies in your project. A coding agent can pair Google result titles, descriptions, and URLs with the questions raised by your code.

Find official documentation

Search a project's documentation domain for a specific feature. Turn the returned titles, descriptions, and URLs into a shortlist for implementation research.

Compare competing search content

Collect results for a query such as "email marketing for nonprofits". Compare titles and descriptions to identify the topics and page formats represented in the returned results.

Prepare a company coverage brief

Search for public coverage of a company such as Adobe or Patagonia. Build a reading list from the returned links and descriptions before reviewing the articles.

Check brand search visibility

Repeat a fixed set of searches for a public business and compare the returned URLs over time. Flag newly appearing links for review without treating their first appearance as their publication date.

Find research on an official domain

Search sites such as nasa.gov for a defined topic. Assemble relevant page titles and links for an editor or researcher to examine.

Build a product comparison reading list

Search for comparisons such as "Notion vs Confluence". Organize the returned links by domain and use their descriptions to choose which comparisons to read.

Discover indexed company announcements

Search a company's website for announcements about a product or initiative. Keep the result titles, descriptions, and source links together for follow-up research.

Questions about Google search results in Claude Code

Can Claude Code use Google search results?

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Google search results like any built-in tool.

How much does Google search results cost in Claude Code?

$0.0013 per run. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.

Do I need a ScrapeCreators account to use Google search results in Claude Code?

No. Spiral runs Google search results on its own ScrapeCreators account. You sign in to Spiral once and never paste a key.

How long does it take to set up Google search results in Claude Code?

About two minutes: add the hosted server, then sign in.

Does Claude Code wait while Google search results runs?

Google search results runs in the background. Claude Code starts the run, checks on it and gives you the json when it's ready.

What does a Google search result contain?

The documented response provides three fields for each returned link: its URL, title, and description. Use those records to choose pages worth reading.

How far can I paginate through results?

You can request pages 1 through 11. Page 12 or higher returns a 400 response.

Does Google include every relevant page?

No. Google does not guarantee crawling, indexing, or displaying a page, even when it follows Search Essentials. A missing result does not establish that the page does not exist.

How quickly do website changes appear in Google?

Google says crawling can take a few days to a few weeks. Search results can therefore lag new pages or edits to existing pages.

Why can the same URL have different descriptions?

Google creates snippets automatically and may show different snippets for different searches. A description is a preview selected for that search, so compare URLs when checking whether two results point to the same page.

Get started

Start using Google search results in Claude Code

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Claude Code:

Set up Claude Code

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options