[Integrations](https://spiral.ai/integrations) › [Claude Code](https://spiral.ai/integrations/claude-code) › [Firecrawl web page content](https://spiral.ai/integrations/claude-code/firecrawl-web-page-content)

# How to Use Firecrawl web page content in Claude Code

Firecrawl returns one URL's content as Markdown, HTML, structured data, or a screenshot. Use it to read a specific documentation page, product page, or public report without crawling an entire website.

|  |  |
| --- | --- |
| Model | Firecrawl web page content |
| Available through | Firecrawl |
| Category | Web |
| Price | $0.00175 per page ($0.00873 with JSON output). Each parsed PDF page: $0.00175. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Firecrawl web page content in Claude Code

- Use Firecrawl web page content on https://nextjs.org/docs/app/getting-started/installation. Compare the instructions with this project's package.json and identify any missing requirements.
- Use Firecrawl web page content on https://react.dev/reference/react/useEffect. Review this project's effects and identify places where the documented cleanup behavior matters.
- Use Firecrawl web page content on https://docs.python.org/3/library/asyncio-task.html. Compare its task-cancellation guidance with the async workers in this repository and propose specific fixes.
- Use Firecrawl web page content on https://www.postgresql.org/docs/current/sql-insert.html. Check this project's upsert queries against the documented ON CONFLICT behavior.
- Use Firecrawl web page content on https://www.rust-lang.org/learn. Save the retrieved page as Markdown in this project's reference directory and draft a learning checklist using only what it contains.

## How to set up Firecrawl web page content 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.

```bash
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.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Firecrawl web page content**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "firecrawl",
    "model": "firecrawl/scrape",
    "input": {
      "url": "<url>"
    }
  }'
```

Then paste one of the prompts above: Claude Code finds Firecrawl web page content on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/claude-code

## Firecrawl web page content tools and prices

- [Firecrawl Scrape · Web Page Content](https://spiral.ai/tools/firecrawl/firecrawl/scrape) (Firecrawl): $0.00175 per page ($0.00873 with JSON output). Each parsed PDF page: $0.00175.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| proxy | basic, enhanced, auto | auto | Specifies the type of proxy to use. - **basic**: Proxies for scraping sites with none to basic anti-bot solutions. |
| maxAge |  | 172800000 | Returns a cached version of the page if it is younger than this age in milliseconds. |
| minAge |  | — | When set, the request only checks the cache and never triggers a fresh scrape. |
| mobile |  | false | Set to true if you want to emulate scraping from a mobile device. Useful for testing responsive pages and taking mobile screenshots. |
| actions |  | — | Actions to perform on the page before grabbing the content |
| formats |  | [{"type":"markdown"}] | Output formats to include in the response. |

## What can you do with Firecrawl web page content in Claude Code?

Turn a specific documentation page into a concrete code review or implementation plan. A coding agent can compare Firecrawl's extracted text with project files and cite the instructions behind each proposed change.

### Check an implementation against official documentation

Read a specific framework guide and compare its instructions with the project's code. Link each proposed correction to the retrieved documentation.

### Build a focused reference collection

Convert selected public documentation pages into Markdown for a support assistant. Retrieve each guide separately so the collection contains the pages people actually need.

### Review release notes

Read a software project's public release page and extract changes relevant to an upgrade. Compare later captures to identify newly published notes.

### Compare published product specifications

Read named manufacturers' product pages and organize their stated dimensions, materials, and compatibility claims into a comparison table.

### Watch public policy pages for revisions

Capture a company's public terms or privacy policy on a schedule. Compare the retrieved text with an earlier capture and report the changed passages.

### Read public PDF reports

Extract text from a public report's PDF URL, including scanned documents supported through OCR. Pull out the sections needed for a research brief.

### Review a page's visual presentation

Capture a screenshot of a named public page and inspect its headings, layout, and visible content alongside the extracted text.

## Overview

- [Firecrawl](https://spiral.ai/providers/firecrawl)
- [All Claude Code guides](https://spiral.ai/integrations/claude-code)

## Firecrawl web page content in other agents

- [Amp](https://spiral.ai/integrations/amp/firecrawl-web-page-content)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/firecrawl-web-page-content)
- [Claude](https://spiral.ai/integrations/claude-desktop/firecrawl-web-page-content)
- [Cline](https://spiral.ai/integrations/cline/firecrawl-web-page-content)
- [Codex](https://spiral.ai/integrations/codex/firecrawl-web-page-content)
- [Cursor](https://spiral.ai/integrations/cursor/firecrawl-web-page-content)
- [Devin](https://spiral.ai/integrations/devin/firecrawl-web-page-content)
- [dots](https://spiral.ai/integrations/dots/firecrawl-web-page-content)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/firecrawl-web-page-content)
- [Gemini](https://spiral.ai/integrations/gemini/firecrawl-web-page-content)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/firecrawl-web-page-content)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/firecrawl-web-page-content)
- [goose](https://spiral.ai/integrations/goose/firecrawl-web-page-content)
- [Grok](https://spiral.ai/integrations/grok/firecrawl-web-page-content)
- [Grok Build](https://spiral.ai/integrations/grok-build/firecrawl-web-page-content)
- [Hermes](https://spiral.ai/integrations/hermes/firecrawl-web-page-content)
- [Instinct](https://spiral.ai/integrations/instinct/firecrawl-web-page-content)
- [Manus](https://spiral.ai/integrations/manus/firecrawl-web-page-content)
- [Muse](https://spiral.ai/integrations/muse/firecrawl-web-page-content)
- [Muse Code](https://spiral.ai/integrations/muse-code/firecrawl-web-page-content)
- [n8n](https://spiral.ai/integrations/n8n/firecrawl-web-page-content)
- [Notion](https://spiral.ai/integrations/notion/firecrawl-web-page-content)
- [opencode](https://spiral.ai/integrations/opencode/firecrawl-web-page-content)
- [Perplexity](https://spiral.ai/integrations/perplexity/firecrawl-web-page-content)
- [Raycast](https://spiral.ai/integrations/raycast/firecrawl-web-page-content)
- [VS Code](https://spiral.ai/integrations/vscode/firecrawl-web-page-content)
- [Windsurf](https://spiral.ai/integrations/windsurf/firecrawl-web-page-content)
- [Zapier](https://spiral.ai/integrations/zapier/firecrawl-web-page-content)

## More Claude Code guides

- [Firecrawl developer search](https://spiral.ai/integrations/claude-code/firecrawl-developer-search)
- [Firecrawl web research](https://spiral.ai/integrations/claude-code/firecrawl-web-research)
- [Firecrawl batch web scraping](https://spiral.ai/integrations/claude-code/firecrawl-batch-web-scraping)
- [Firecrawl web search](https://spiral.ai/integrations/claude-code/firecrawl-web-search)
- [Exa web search](https://spiral.ai/integrations/claude-code/exa-web-search)
- [Firecrawl website URLs](https://spiral.ai/integrations/claude-code/firecrawl-website-urls)

## Questions about Firecrawl web page content in Claude Code

**Can Claude Code use Firecrawl web page content?**

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Firecrawl web page content like any built-in tool.

**How much does Firecrawl web page content cost in Claude Code?**

$0.00175 per page ($0.00873 with JSON output). Each parsed PDF page: $0.00175. 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 Firecrawl account to use Firecrawl web page content in Claude Code?**

No. Spiral runs Firecrawl web page content on its own Firecrawl account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Firecrawl web page content in Claude Code?**

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

**Does Claude Code wait while Firecrawl web page content runs?**

Firecrawl web page content runs in the background. Claude Code starts the run, checks on it and gives you the json when it's ready.

**Does Firecrawl capture a whole website in one scrape?**

Scrape retrieves one URL's page content. A documentation homepage does not include every linked guide; those pages require their own requests or a separate crawl.

**How fresh is the returned page?**

Firecrawl's default cache window is two days. It can return a cached capture within that window, so request a fresh capture when checking a recently changed announcement or policy.

**Can Firecrawl read scanned reports?**

Firecrawl supports both text-based and scanned PDFs, including OCR for scanned content. Supply the report's PDF URL to retrieve its extracted content as Markdown.

**Does a successful response mean the source page was available?**

Firecrawl can report a successful request even when the target website returned an error such as 403 or 404. Check the target page status in the returned metadata before treating the content as a valid capture.

**Is structured JSON copied directly from the website?**

Firecrawl's JSON mode uses an LLM to extract requested fields from a single page and can follow a supplied schema. Those fields are generated extraction results, rather than necessarily being the website's own underlying JSON.

