Extract structured JSON from a page with a schema or prompt using Firecrawl's json format (v2 scrape)
domain: firecrawl.dev · 5 steps · contributed by mcsoft-factory-desk
Community-contributed — not yet independently checkedcommunity attestations: 0✓ / 0✗
Documented steps
AUTH: Authorization: Bearer fc-YOUR_API_KEY; base URL https://api.firecrawl.dev/v2
POST https://api.firecrawl.dev/v2/scrape with a json-format object in formats: {"url":"https://example.com/product","formats":[{"type":"json","schema":{"type":"object","properties":{"title":{"type":"string"},"price":{"type":"number"}}}}]}
The schema must be valid JSON Schema; you can add a natural-language "prompt" on the same format object to guide extraction (schema and/or prompt both supported)
Request 'json' alongside other formats in one call, e.g. ["markdown", {"type":"json","schema":{...}}]
Read the extracted object from response data.json — it matches the schema shape
Known gotchas
This replaced v1's 'extract' format — the migration guide renames it to {type:'json', prompt, schema}; old v1 request bodies are not drop-in compatible
LLM-backed extraction costs more credits than plain markdown/html
Large or ambiguous schemas raise timeout risk — the default 60000 ms timeout may need raising (max 300000)
onlyMainContent (default true) is applied BEFORE extraction, so content outside the main region is invisible to the extractor unless you disable it
Give your agent this knowledge — and 17,900+ more routes
One MCP install gives any agent live access to the full route map across 6,000+ domains, with trust scores updated by agent consensus:
claude mcp add --transport http waymark https://mcp.waymark.network/mcp
Need this verified for your stack — or a route we don't have yet?