{ "service": "scrapfly", "displayName": "Scrapfly", "categories": [ "Developer Tools", "Data" ], "authTypes": [ "api_key" ], "auth": [ { "type": "api_key", "label": "API Key", "placeholder": "SCRAPFLY_API_KEY", "description": "Scrapfly API key used as the key query parameter.", "extraFields": [] } ], "homepageUrl": "https://scrapfly.io/", "actions": [ { "id": "scrapfly.get_monitoring_metrics", "service": "scrapfly", "name": "get_monitoring_metrics", "description": "Retrieve Scrapfly monitoring metrics for the connected API key.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": { "aggregation": { "type": "string", "minLength": 1, "description": "The metrics aggregation list accepted by Scrapfly, such as account, project, or account,project,target." }, "period": { "type": "string", "enum": [ "last5m", "last1h", "last7d", "last24h", "subscription" ], "description": "The monitoring period to retrieve." }, "start": { "type": "string", "minLength": 1, "description": "The UTC start date accepted by Scrapfly when period is omitted." }, "end": { "type": "string", "minLength": 1, "description": "The UTC end date accepted by Scrapfly when period is omitted." }, "group_subdomain": { "type": "boolean", "description": "Whether target aggregation should group subdomains." } }, "additionalProperties": false, "description": "The input payload for retrieving Scrapfly monitoring metrics." }, "outputSchema": { "type": "object", "properties": { "metrics": { "type": "object", "properties": {}, "additionalProperties": true, "description": "Monitoring metrics returned by Scrapfly." }, "metadata": { "type": "object", "properties": { "status_code": { "type": "integer", "description": "The HTTP status code returned by Scrapfly." }, "api_cost": { "anyOf": [ { "type": "integer", "description": "The API credit cost reported by Scrapfly." }, { "type": "null" } ] }, "remaining_api_credit": { "anyOf": [ { "type": "integer", "description": "Remaining API credit reported by Scrapfly." }, { "type": "null" } ] }, "reject_code": { "anyOf": [ { "type": "string", "description": "The Scrapfly reject code when a scrape is rejected." }, { "type": "null" } ] }, "reject_description": { "anyOf": [ { "type": "string", "description": "The Scrapfly reject documentation URL when a scrape is rejected." }, { "type": "null" } ] }, "reject_retryable": { "anyOf": [ { "type": "string", "description": "Whether Scrapfly reported the rejection as retryable." }, { "type": "null" } ] } }, "additionalProperties": false, "description": "Metadata collected from Scrapfly response headers." }, "headers": { "type": "object", "additionalProperties": { "type": "string", "description": "One response header value." }, "description": "Response headers returned by Scrapfly." } }, "additionalProperties": false, "description": "The response returned when retrieving Scrapfly monitoring metrics." } }, { "id": "scrapfly.scrape", "service": "scrapfly", "name": "scrape", "description": "Scrape one public URL through Scrapfly and return the documented JSON response envelope.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": { "url": { "type": "string", "description": "The public URL Scrapfly should scrape.", "format": "uri" }, "method": { "type": "string", "enum": [ "GET", "POST", "PUT", "PATCH", "HEAD", "OPTIONS" ], "description": "The HTTP method Scrapfly should use against the target URL." }, "body": { "type": "string", "description": "The raw request body Scrapfly should send to the target URL." }, "content_type": { "type": "string", "minLength": 1, "description": "The Content-Type header for the target request body." }, "format": { "type": "string", "minLength": 1, "description": "The content format Scrapfly should return." }, "country": { "type": "string", "minLength": 2, "description": "The proxy country selection accepted by Scrapfly, such as us, us,ca,mx, or -gb." }, "proxy_pool": { "type": "string", "enum": [ "public_datacenter_pool", "public_residential_pool" ], "description": "The Scrapfly proxy pool to use for the scrape." }, "render_js": { "type": "boolean", "description": "Whether Scrapfly should render JavaScript before returning." }, "asp": { "type": "boolean", "description": "Whether Scrapfly should enable Anti Scraping Protection." }, "retry": { "type": "boolean", "description": "Whether Scrapfly should retry the scrape request." }, "timeout": { "type": "integer", "minimum": 1000, "maximum": 150000, "description": "The scrape timeout in milliseconds." }, "wait_for_selector": { "type": "string", "minLength": 1, "description": "The CSS selector Scrapfly should wait for before returning content." }, "cache": { "type": "boolean", "description": "Whether Scrapfly should use cached scrape results when available." }, "cache_ttl": { "type": "integer", "minimum": 1, "description": "The cache time-to-live in seconds." }, "cache_clear": { "type": "boolean", "description": "Whether Scrapfly should clear any matching cached result." }, "session": { "type": "string", "minLength": 1, "maxLength": 255, "description": "The Scrapfly session name used to keep browsing state." }, "session_sticky_proxy": { "type": "boolean", "description": "Whether Scrapfly should keep the session proxy sticky." }, "headers": { "type": "object", "additionalProperties": { "type": "string", "description": "A target request header value." }, "description": "Target request headers Scrapfly should send to the scraped website." }, "tags": { "type": "array", "items": { "type": "string", "minLength": 1, "description": "One Scrapfly monitoring tag." }, "description": "Tags for grouping the scrape in Scrapfly monitoring." }, "correlation_id": { "type": "string", "minLength": 1, "description": "A caller-provided correlation identifier for monitoring." }, "debug": { "type": "boolean", "description": "Whether Scrapfly should expose debug data for the scrape." } }, "additionalProperties": false, "required": [ "url" ], "description": "The input payload for scraping a URL with Scrapfly." }, "outputSchema": { "type": "object", "properties": { "result": { "type": "object", "properties": { "content": { "description": "The scraped content, a large object URL, or encoded binary content." }, "status_code": { "type": "integer", "description": "The HTTP status code returned by the target website." }, "format": { "type": "string", "description": "The Scrapfly result content format." } }, "additionalProperties": true, "description": "The result object returned by Scrapfly." }, "config": { "type": "object", "properties": {}, "additionalProperties": true, "description": "The scrape configuration returned by Scrapfly." }, "context": { "type": "object", "properties": {}, "additionalProperties": true, "description": "Additional context returned by Scrapfly." }, "metadata": { "type": "object", "properties": { "status_code": { "type": "integer", "description": "The HTTP status code returned by Scrapfly." }, "api_cost": { "anyOf": [ { "type": "integer", "description": "The API credit cost reported by Scrapfly." }, { "type": "null" } ] }, "remaining_api_credit": { "anyOf": [ { "type": "integer", "description": "Remaining API credit reported by Scrapfly." }, { "type": "null" } ] }, "reject_code": { "anyOf": [ { "type": "string", "description": "The Scrapfly reject code when a scrape is rejected." }, { "type": "null" } ] }, "reject_description": { "anyOf": [ { "type": "string", "description": "The Scrapfly reject documentation URL when a scrape is rejected." }, { "type": "null" } ] }, "reject_retryable": { "anyOf": [ { "type": "string", "description": "Whether Scrapfly reported the rejection as retryable." }, { "type": "null" } ] } }, "additionalProperties": false, "description": "Metadata collected from Scrapfly response headers." }, "headers": { "type": "object", "additionalProperties": { "type": "string", "description": "One response header value." }, "description": "Response headers returned by Scrapfly." } }, "additionalProperties": false, "description": "The response returned when scraping with Scrapfly." } } ] }