Firecrawl scrape actions on Sume: 8 actions, no write or press
Sume's crawl_scrape accepts up to 8 actions of four types: wait, scroll, click, executeJavascript. Firecrawl's write, press and pdf have no match.

Sume's scrape takes at most 8 actions, each one of wait, scroll, click or executeJavascript. Firecrawl lists more types (write, press, screenshot, scrape, pdf) and says up to 50 per request. A Firecrawl actions array that types into a field or presses a key needs rewriting before it will pass Sume's schema.
Which Firecrawl actions map to Sume?
Firecrawl's guide lists nine action types. Sume's OpenAPI schema accepts four of them.
| Firecrawl action | In Sume's schema? | Notes |
|---|---|---|
wait | Yes | milliseconds 1 to 10000 |
scroll | Yes | direction up or down, optional selector |
click | Yes | selector required, up to 500 characters |
executeJavascript | Yes | script up to 4000 characters |
write, press | No | Not accepted |
screenshot | As a format | Request "screenshot" in formats |
scrape | Not needed | The call itself is the scrape |
pdf | No | Not in the schema |
What are the limits?
The array holds up to 8 items, and each executeJavascript script is capped at 4000 characters. Firecrawl's guide says 50 actions per request, while its API schema page shows maxItems 10; Sume's cap is 8 in both the tool description and the schema.
How do I replace a typing step?
The docs describe no typing or key-press action. Sume reads pages that are reachable by URL, so put the query in the URL where the site allows it, then scrape. Whether a script in executeJavascript can drive a form is not documented, so test it on the page before depending on it.
curl -X POST https://api.sume.com/v1/firecrawl/scrape \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"url": "https://example.com/catalog?page=2",
"formats": ["markdown", "screenshot"],
"actions": [
{ "type": "click", "selector": "button.load-more" },
{ "type": "wait", "milliseconds": 1500 }
]
}'Where do I read the rest of the tool contract?
The tool is listed in MCP tools and gates. Timing rules are in the wait budget post.
Sources
Related posts
More in Developers
- Firecrawl scrape formats: the seven Sume supports
Firecrawl scrape lists summary, branding, question and more. Sume's scrape accepts seven formats: markdown, links, html, json, screenshot, rawHtml, images.
- Firecrawl search endpoint: limit 100 vs Sume's limit of 10
Firecrawl's /search takes limit up to 100 plus sources and tbs. Sume's /v1/firecrawl/search takes a query and limit 1-10, so scrape the hits you need next.
- FLUX image URL expires after 10 minutes: what Sume returns
Black Forest Labs says generated FLUX image URLs expire after 10 minutes. Sume returns Sume-hosted signed URLs; here is how to fetch and keep the file.
- frame_images plus input_references in one request: which wins?
When a Sume video request carries both frame_images and input_references, frame_images wins and the job runs as image-to-video. What that means for references.
Written by Sume