Firecrawl MCP timeout: Sume crawl_scrape's 35, 40 and 45 s deadlines
A synchronous crawl_scrape call has three deadlines: client abort at 35 s, MCP at 40 s, host watchdog at 45 s. Narrow the page or use crawl_site.
A crawl_scrape call made through MCP is synchronous and ends at one of three deadlines: 35 seconds for the client abort, 40 seconds for the MCP deadline, 45 seconds for the ACP host watchdog. Raising your own client timeout does not move them. When a page misses its deadline the call fails with a typed timeout error; narrow the page or switch to crawl_site.
The numbers are from the crawl_scrape tool description in Sume's MCP server code, read 2026-09-30.
Which deadline fires first?
They stack: the client aborts first, then the MCP server, then the host watchdog as a last backstop.
| Order | Layer | Seconds |
|---|---|---|
| 1 | Client deadline/abort | 35 |
| 2 | MCP deadline | 40 |
| 3 | ACP host watchdog | 45 |
Can I wait on a scrape with jobs_wait?
No. The description states: "No jobs_wait for scrape." A scrape returns a result or a typed timeout error in the same call.
What should the agent do after a timeout?
Report that the page did not return in time and stop, as the description says. Do not bypass with web_fetch, raw HTML scripts or guessed CDN URLs. Then change the request, not the client.
Which tool handles many pages?
crawl_site is the async path. Per MCP tools and gates it is a write tool that takes an idempotency_key, then you call jobs_wait and crawl_get on the same id. For the wait-and-resume pattern in general, see jobs_wait for long jobs.
Sources
Related posts
More in Developers
- Firecrawl question format: json_prompt on Sume scrape
Firecrawl added a Question format to /scrape. Sume has none; ask with json_prompt (up to 2,000 characters) or json_schema under formats: [json].
- 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.
- 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.
Written by Sume