How to Use Firecrawl Scrape in OpenClaw
Firecrawl Scrape turns web pages into Markdown, HTML, or screenshots, including pages with JavaScript content. In OpenClaw, use it to collect source material for a brief, check a page update, or capture a mobile view.
Prompts to try with Firecrawl Scrape in OpenClaw
Copy an example into OpenClaw, or ask in your own words.
Use Firecrawl Scrape to read https://docs.firecrawl.dev/features/scrape as Markdown. Give me a brief on page actions and caching, with a supporting passage for each recommendation.
Use Firecrawl Scrape to fetch the release-notes URL I shared, requesting a fresh scrape. Compare the content with the earlier version in this conversation. List added, changed, and removed statements, and include the source URL.
Use Firecrawl Scrape on the page URL I shared. Emulate a mobile device, wait three seconds before capture, and return a screenshot plus Markdown. Keep the captured text available alongside the image.
Use Firecrawl Scrape on the FAQ page I shared. Click the question I identified, wait for its answer to appear, then capture the content as Markdown. Quote the answer and include the page URL.
Every Monday at 9am: scrape https://example.com/pricing with Firecrawl Scrape and turn it into a comparison table.
How to set up Firecrawl Scrape in OpenClaw
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send OpenClaw this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use Spiral's MCP server
- Add the server
On the machine that runs OpenClaw's Gateway:
openclaw mcp add spiral \ --url https://api.spiral.ai/mcp \ --transport streamable-http \ --auth oauth
- Sign in
In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.
openclaw mcp login spiral
- Reload and check
A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.
openclaw mcp reload openclaw mcp doctor spiral --probe
Use the Spiral CLI
- 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
- Create an API key
In the console, under API keys.
- Run Firecrawl Scrape
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": "firecrawl", "model": "firecrawl/scrape", "input": { "url": "<url>" } }'
Then paste one of the prompts above: OpenClaw finds Firecrawl Scrape on Spiral, shows the price and runs it.
Firecrawl Scrape providers and prices
Spiral runs Firecrawl Scrape through Firecrawl. Open a card for today's price, with every fee included.
$0.00175 per page ($0.00873 with JSON output). Each parsed PDF page: $0.00175.
Settings you can ask for
Ask OpenClaw for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Proxy | basic, enhanced, or auto | auto | Specifies the type of proxy to use.
|
| Max age | a whole number | 172800000 | Returns a cached version of the page if it is younger than this age in milliseconds. |
| Min age | a whole number | When set, the request only checks the cache and never triggers a fresh scrape. | |
| Mobile | on or off | off | Set to true if you want to emulate scraping from a mobile device. Useful for testing responsive pages and taking mobile screenshots. |
| Timeout | 1000 to 300000 | 60000 | Timeout in milliseconds for the request. Minimum is 1000 (1 second). Default is 60000 (60 seconds). Maximum is 300000 (300 seconds). |
| Wait for | a whole number up to 60000 | 0 | Specify a delay in milliseconds before fetching the content, allowing the page sufficient time to load. |
| Block ads | on or off | on | Enables ad-blocking and cookie popup blocking. |
| Lockdown | on or off | off | If true, serves the request from Firecrawl's cache only and never makes an outbound request to the target URL. |
| Tool detail | compact, summary, or full | How much of each tool contract to return in | |
| Domain tools | on or off | off | When true on an ordinary URL scrape, |
| Store in cache | on or off | on | If true, the page will be stored in the Firecrawl index and cache. |
| Only main content | on or off | on | Only return the main content of the page excluding headers, navs, footers, etc. This is a deterministic HTML-level filter applied before markdown is generated; no LLM is involved. |
| Only clean content | on or off | off | Beta. Run an additional LLM-based pass over the generated markdown to remove residual boilerplate that |
| Zero data retention | on or off | off | If true, this will enable zero data retention for this scrape. To enable this feature, please contact [email protected] |
| Remove base64 images | on or off | on | Removes all base 64 images from the markdown output, which may be overwhelmingly long. |
| Skip tls verification | on or off | on | Skip TLS certificate verification when making requests. |
| Check prompt injection | on or off | off | When enabled, scans the page content for prompt injection attempts before any LLM-backed format (such as json, summary or question) runs. |
Every API field of Firecrawl Scrape · Web Page Content is on its tool page: open its card above.
What can you do with Firecrawl Scrape in OpenClaw?
Ask OpenClaw to read a specific page with Firecrawl, then summarize the returned content around your question. For repeat checks, specify how fresh the content must be and what earlier version to compare against.
Prepare a source-based brief
Request Markdown from a documentation page or article, then ask OpenClaw to answer a specific question using passages from the returned text.
Compare page updates
Request a fresh scrape of release notes or a policy page. Ask OpenClaw to compare it with an earlier copy you provide and report the changed wording.
Capture a mobile page
Request mobile emulation, a screenshot, and Markdown together when you need both the page’s appearance and its text.
Read an expanded answer
Specify the tab or FAQ question to click before capture. Ask OpenClaw to base its response on the content returned after that action.
Choose freshness for recurring checks
For a recurring page review, state whether a recent cached copy is acceptable or each check needs a fresh scrape.
Read a page after a loading delay
If an initial capture misses expected text, request a short wait before another capture and check whether the returned content includes it.
Firecrawl Scrape success rate and speed on Spiral
Success and speed over the last 24 hours, across every run of these tools on Spiral.
| Tool | Success | Median time | Runs |
|---|---|---|---|
| Firecrawl Scrape · Web Page Content | 94.2% | 3.7s | 910 |
More on Firecrawl Scrape and OpenClaw
Overview
Questions about Firecrawl Scrape in OpenClaw
Can OpenClaw use Firecrawl Scrape?
Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Firecrawl Scrape like any built-in tool.
How much does Firecrawl Scrape cost in OpenClaw?
$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 OpenClaw plan is separate.
Do I need a Firecrawl account to use Firecrawl Scrape in OpenClaw?
No. Spiral runs Firecrawl Scrape 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 Scrape in OpenClaw?
About two minutes: add the server, then sign in, then reload and check.
Does OpenClaw wait while Firecrawl Scrape runs?
Firecrawl Scrape runs in the background. OpenClaw starts the run, checks on it and gives you the json when it's ready.
Can Firecrawl Scrape read JavaScript-rendered pages?
Yes. Firecrawl documents support for JavaScript-heavy pages and dynamic apps.
Does Firecrawl Scrape always fetch the latest page?
It can return a cached copy within the default two-day freshness window. Ask for a fresh scrape when checking a recent announcement or page change.
Can Firecrawl Scrape click a button before extracting content?
Yes. Page actions support clicks, scrolling, and waits before capture. Specify the button or section you want opened.
Can Firecrawl Scrape take mobile screenshots?
Yes. Mobile emulation supports mobile screenshots and responsive-page checks.
Which Firecrawl Scrape output should I request for a summary?
Start with Markdown so you can review the source text alongside OpenClaw’s summary. Request a screenshot when the page’s appearance also matters.
Start using Firecrawl Scrape in OpenClaw
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into OpenClaw:
set up https://spiral.ai/SKILL.md