{ "id": "firecrawl.scrape", "object": "tool", "name": "Firecrawl Scrape", "summary": "Scrape one URL into clean markdown, HTML, or schema-shaped JSON.", "description": "Turn a single URL into clean Markdown, HTML, links, images, a summary, or a screenshot — and add a `json` format object to LLM-extract structured data against your own schema or prompt. Anti-bot handling is included at no extra cost: `proxy` defaults to 'auto', which retries with enhanced proxies when the plain fetch is blocked, at the same price. `maxAge` reuses a recent cached copy for a much faster response; set 0 to force a live fetch. PDFs parse natively and bill per PDF page. Two costs to know before choosing this endpoint: a page answering 403 or 404 is still charged, because the browser and proxy were already spent — check `metadata.statusCode` before retrying a blocked URL — and the LLM formats (`json`, `question`, `highlights`, `audio`, `video`) each add four times the base page cost.\n\nRaw firecrawl#scrape endpoint: input is { body, queryParams, pathParams } as the provider documents them (https://docs.firecrawl.dev/api-reference/endpoint/scrape).", "category": "web", "hosted_by": "Firecrawl", "runtime": "partner", "side_effects": false, "status": "live", "credits": 0, "price": null, "providers": [ { "id": "firecrawl", "name": "Firecrawl", "price": null, "own_key_only": true } ], "mcp_name": "firecrawl_scrape", "input_schema": { "type": "object", "properties": { "body": { "type": "object", "properties": { "formats": { "description": "Output formats. Defaults to ['markdown'].", "type": "array", "items": { "anyOf": [ { "type": "string", "enum": [ "markdown", "summary", "html", "rawHtml", "rawBase64", "links", "images", "screenshot", "branding", "product", "menu", "audio", "video" ] }, { "type": "object", "properties": { "type": { "type": "string", "enum": [ "markdown", "summary", "html", "rawHtml", "rawBase64", "links", "images", "branding", "product", "menu", "audio", "video" ] } }, "required": [ "type" ] }, { "type": "object", "properties": { "type": { "type": "string", "const": "screenshot" }, "fullPage": { "type": "boolean" }, "quality": { "type": "integer", "minimum": 1, "maximum": 100 }, "viewport": { "type": "object", "properties": { "width": { "type": "integer", "minimum": -9007199254740991, "maximum": 9007199254740991 }, "height": { "type": "integer", "minimum": -9007199254740991, "maximum": 9007199254740991 } }, "required": [ "width", "height" ] } }, "required": [ "type" ] }, { "type": "object", "properties": { "type": { "type": "string", "const": "json" }, "schema": { "description": "JSON Schema the extracted object must conform to.", "type": "object", "propertyNames": { "type": "string" }, "additionalProperties": {} }, "prompt": { "description": "What to extract from the page.", "type": "string" }, "checkPromptInjection": { "description": "Scan the page for prompt-injection attempts before extracting. Adds 4 credits when the check runs; a detection fails the request with 403 SCRAPE_PROMPT_INJECTION_DETECTED.", "type": "boolean" } }, "required": [ "type" ] }, { "type": "object", "properties": { "type": { "type": "string", "const": "changeTracking" }, "modes": { "type": "array", "items": { "type": "string", "enum": [ "git-diff", "json" ] } }, "schema": { "type": "object", "propertyNames": { "type": "string" }, "additionalProperties": {} }, "prompt": { "type": "string" }, "tag": { "type": [ "string", "null" ] } }, "required": [ "type" ], "description": "Requires 'markdown' to also be in the formats array." }, { "type": "object", "properties": { "type": { "type": "string", "const": "question" }, "question": { "type": "string", "maxLength": 10000, "description": "Natural-language question about the page; the answer lands in the response's `answer` field." } }, "required": [ "type", "question" ] }, { "type": "object", "properties": { "type": { "type": "string", "const": "highlights" }, "query": { "type": "string", "maxLength": 10000, "description": "Source-text selection request; the selection lands in the response's `highlights` field." } }, "required": [ "type", "query" ] } ] } }, "onlyMainContent": { "description": "Return only the main content, excluding headers, navs and footers (default true). A deterministic HTML-level filter; no LLM.", "type": "boolean" }, "onlyCleanContent": { "description": "Beta. An additional LLM pass over the markdown to remove residual boilerplate (default false).", "type": "boolean" }, "includeTags": { "description": "CSS selectors to include, matched against the original page DOM.", "type": "array", "items": { "type": "string" } }, "excludeTags": { "description": "CSS selectors to exclude, matched against the original page DOM.", "type": "array", "items": { "type": "string" } }, "maxAge": { "description": "Serve a cached copy younger than this many ms (default 172800000, 2 days). 0 forces a live fetch. Cached results still cost a full credit — caching buys speed, not credits.", "type": "integer", "minimum": 0, "maximum": 9007199254740991 }, "minAge": { "description": "Cache-ONLY lookup: never triggers a fresh scrape. A miss returns 404 SCRAPE_NO_CACHED_DATA. Set 1 to accept any cached data.", "type": "integer", "minimum": 0, "maximum": 9007199254740991 }, "headers": { "description": "Headers to send with the request (cookies, user-agent, etc.).", "type": "object", "propertyNames": { "type": "string" }, "additionalProperties": { "type": "string" } }, "waitFor": { "description": "Extra ms to wait after load, on top of Firecrawl's smart wait (default 0).", "type": "integer", "minimum": 0, "maximum": 9007199254740991 }, "mobile": { "description": "Emulate a mobile device (default false).", "type": "boolean" }, "skipTlsVerification": { "description": "Skip TLS certificate verification (default true).", "type": "boolean" }, "timeout": { "description": "Per-page deadline in ms (default 60000, max 300000).", "type": "integer", "minimum": 1000, "maximum": 300000 }, "parsers": { "description": "File processing. Defaults to ['pdf'], which parses PDFs to markdown at 1 credit per PDF page. An EMPTY array returns the PDF as base64 at a flat 1 credit.", "type": "array", "items": { "anyOf": [ { "type": "string", "const": "pdf" }, { "type": "object", "properties": { "type": { "type": "string", "const": "pdf" }, "mode": { "description": "'fast': embedded text only. 'auto' (default): fast with OCR fallback. 'ocr': force OCR on every page.", "type": "string", "enum": [ "fast", "auto", "ocr" ] }, "maxPages": { "description": "Cap the number of PDF pages parsed.", "type": "integer", "minimum": 1, "maximum": 10000 }, "pages": { "description": "Also return per-page markdown in `pages`. No additional cost.", "type": "boolean" }, "blocks": { "description": "Also return per-page typed layout blocks. No additional cost.", "type": "boolean" }, "pageMarkers": { "description": "Annotate page breaks in the markdown. No additional cost.", "type": "boolean" } }, "required": [ "type" ] } ] } }, "actions": { "description": "Browser actions to run before scraping. Max 50; the combined wait time must not exceed 60 s. Not supported for PDFs.", "type": "array", "items": { "anyOf": [ { "type": "object", "properties": { "type": { "type": "string", "const": "wait" }, "milliseconds": { "type": "integer", "minimum": 1, "maximum": 9007199254740991 }, "selector": { "type": "string" } }, "required": [ "type" ], "description": "Wait for a duration OR for an element — provide one." }, { "type": "object", "properties": { "type": { "type": "string", "const": "screenshot" }, "fullPage": { "type": "boolean" }, "quality": { "type": "integer", "minimum": 1, "maximum": 100 }, "viewport": { "type": "object", "properties": { "width": { "type": "integer", "minimum": -9007199254740991, "maximum": 9007199254740991 }, "height": { "type": "integer", "minimum": -9007199254740991, "maximum": 9007199254740991 } }, "required": [ "width", "height" ] } }, "required": [ "type" ] }, { "type": "object", "properties": { "type": { "type": "string", "const": "click" }, "selector": { "type": "string" }, "all": { "type": "boolean" } }, "required": [ "type", "selector" ] }, { "type": "object", "properties": { "type": { "type": "string", "const": "write" }, "text": { "type": "string" } }, "required": [ "type", "text" ] }, { "type": "object", "properties": { "type": { "type": "string", "const": "press" }, "key": { "type": "string" } }, "required": [ "type", "key" ] }, { "type": "object", "properties": { "type": { "type": "string", "const": "scroll" }, "direction": { "type": "string", "enum": [ "up", "down" ] }, "selector": { "type": "string" } }, "required": [ "type" ] }, { "type": "object", "properties": { "type": { "type": "string", "const": "scrape" } }, "required": [ "type" ] }, { "type": "object", "properties": { "type": { "type": "string", "const": "executeJavascript" }, "script": { "type": "string" } }, "required": [ "type", "script" ] }, { "type": "object", "properties": { "type": { "type": "string", "const": "pdf" }, "format": { "type": "string", "enum": [ "A0", "A1", "A2", "A3", "A4", "A5", "A6", "Letter", "Legal", "Tabloid", "Ledger" ] }, "landscape": { "type": "boolean" }, "scale": { "type": "number" } }, "required": [ "type" ] } ] } }, "location": { "type": "object", "properties": { "country": { "description": "ISO 3166-1 alpha-2 country code (e.g. 'US', 'AU', 'DE', 'JP'). Defaults to 'US'.", "type": "string", "pattern": "^[A-Z]{2}$" }, "languages": { "description": "Preferred languages and locales in order of priority (e.g. ['en-US']). Defaults to the language of the location.", "type": "array", "items": { "type": "string" } } } }, "removeBase64Images": { "description": "Replace base64 image URLs in markdown with a placeholder (default true). Does not affect html or rawHtml.", "type": "boolean" }, "blockAds": { "description": "Enable ad-blocking and cookie-popup blocking (default true).", "type": "boolean" }, "proxy": { "description": "'auto' (default) retries with enhanced anti-bot proxies when the basic fetch is blocked. Enhanced proxies carry NO surcharge.", "type": "string", "enum": [ "basic", "enhanced", "auto" ] }, "storeInCache": { "description": "Store the page in the Firecrawl index and cache (default true). Sensitive options (actions, headers) force this false.", "type": "boolean" }, "lockdown": { "description": "Serve from Firecrawl's cache only, never fetching the target (default false). Billed 5 credits on a hit, 1 on a miss; a miss returns 404 SCRAPE_LOCKDOWN_CACHE_MISS.", "type": "boolean" }, "redactPII": { "description": "Redact personally identifiable information from the returned markdown (default false). Costs +4 credits per page.", "anyOf": [ { "type": "boolean" }, { "type": "object", "properties": { "mode": { "description": "Redaction strategy. 'accurate' (default) is model-only and optimized for precision, 'aggressive' increases recall with extra heuristics, 'fast' uses heuristics without the model call.", "type": "string", "enum": [ "accurate", "aggressive", "fast" ] }, "entities": { "description": "Restrict redaction to these entity buckets. Omit to redact all.", "type": "array", "items": { "type": "string", "enum": [ "PERSON", "EMAIL", "PHONE", "LOCATION", "FINANCIAL", "SECRET" ] } }, "replaceStyle": { "description": "'tag' (default) replaces spans with placeholders like , 'mask' replaces characters with *, 'remove' deletes the span.", "type": "string", "enum": [ "tag", "mask", "remove" ] } } } ] }, "profile": { "description": "Persistent browser storage shared by scrapes using the same name.", "type": "object", "properties": { "name": { "type": "string", "minLength": 1, "maxLength": 128 }, "saveChanges": { "type": "boolean" } }, "required": [ "name" ] }, "threatProtection": { "type": "object", "properties": { "mode": { "description": "URL scanning mode for this request. 'normal' checks URLs against Google Web Risk and costs +2 credits per URL scanned.", "type": "string", "enum": [ "off", "normal" ] }, "riskScoreThreshold": { "type": "integer", "minimum": 0, "maximum": 100 }, "blacklist": { "maxItems": 1000, "type": "array", "items": { "type": "string" } }, "whitelist": { "maxItems": 1000, "type": "array", "items": { "type": "string" } }, "blockedTlds": { "maxItems": 1000, "type": "array", "items": { "type": "string" } }, "failurePolicy": { "type": "string", "enum": [ "open", "closed" ] } } }, "auditMetadata": { "type": "object", "properties": { "username": { "type": "string", "maxLength": 1024, "description": "The username associated with the request." } }, "required": [ "username" ] }, "url": { "type": "string", "format": "uri", "description": "The URL to scrape.", "examples": [ "https://example.com/pricing" ] }, "zeroDataRetention": { "description": "Persist nothing beyond the lifetime of the request (default false). Enterprise-gated; costs +1 credit per page and is incompatible with the screenshot format.", "type": "boolean" } }, "required": [ "url" ] } }, "required": [ "body" ], "additionalProperties": false }, "kind": "endpoint" }