firecrawl-scrape
firecrawl scrape
Via the Firecrawl MCP (preferred)
This plugin bundles the Firecrawl MCP server. When it's connected, prefer the native firecrawl_scrape tool over the CLI — it needs no local install and authenticates through the plugin's one-time browser sign-in. Pass the same capabilities described below (formats, JSON extraction with a schema, waitFor, proxy/stealth) as tool arguments. The firecrawl CLI commands below are the fallback for when the MCP isn't connected.
Scrape one or more URLs. Returns clean, LLM-optimized markdown. Multiple URLs are scraped concurrently.
Execute an Alexandria capability
firecrawl_scrape also runs Alexandria data providers. Pass alexandria instead of url (exactly one of the two) with the provider, capability, and options that discovery returned, optionally as an array of up to ten calls, and read the results in data.alexandria[]. Check each item for an error with a code; a provider error never fails the batch as a whole. Discovery and contracts come from firecrawl_search (source alexandria) and firecrawl_find_tools; see firecrawl-alexandria for the flow, pricing, and provider terms. In the CLI the same call is firecrawl scrape <provider>/<capability> --options '<json>'.
When to use
- You have a specific URL and want its content
- The page is static or JS-rendered (SPA)
- Step 2 in the workflow escalation pattern: search → scrape → map → crawl → interact