Firecrawl structured data extraction
Extract structured data from pages using LLMs. Needs urls.
Inputs
- URLs
- A list of text valuesRequired · urls
- Prompt
- Prompt to guide the extraction processOptional · prompt
- Schema
- Schema to define the structure of the extracted dataOptional · schema
- Enable web search
- When true, the extraction will use web search to find additional dataOptional · enableWebSearch
- Ignore sitemap
- When true, sitemap.xml files will be ignored during website scanningOptional · ignoreSitemap
- Include subdomains
- When true, subdomains of the provided URLs will also be scannedOptional · includeSubdomains
- Show sources
- When true, the sources used to extract the data will be included in the response as `sources` keyOptional · showSources
- Scrape options
- An objectOptional · scrapeOptions
- Ignore invalid URLs
- If invalid URLs are specified in the urls array, they will be ignoredOptional · ignoreInvalidURLs
- Threat protection
- Per-request [Threat Protection](https://docs.firecrawl.dev/features/threat-protection) overrideOptional · threatProtection
Pricing
- Price
- Price pending
- Billing
- No price is recorded for this tool yet.
Call
Your agent reads the schema and the price with inspect_tool before it runs the tool.
- MCP call
- cURL command
- TypeScript
- Tool ID
Alternatives
Connect your agent to 2,400+ tools for free
Sign in with Google or GitHub. No card required.