AI Crawler Policy Auditor
Pricing
from $4.90 / 1,000 page auditeds
Go to Apify Store
AI Crawler Policy Auditor
Audit robots and AI crawler policy signals for AI crawler access, blocking, and site-readiness.
AI Crawler Policy Auditor
Pricing
from $4.90 / 1,000 page auditeds
Audit robots and AI crawler policy signals for AI crawler access, blocking, and site-readiness.
You can access the AI Crawler Policy Auditor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "80vNFOXNuAAgowY5A" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~ai-crawler-policy-auditor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-ai-crawler-policy-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/junipr~ai-crawler-policy-auditor/runs": { "post": { "operationId": "runs-sync-junipr-ai-crawler-policy-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/junipr~ai-crawler-policy-auditor/run-sync": { "post": { "operationId": "run-sync-junipr-ai-crawler-policy-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "targets": { "title": "Policy Targets", "type": "array", "description": "Robots.txt and page-signal snapshots to audit. Defaults to a local fixture that makes no network calls.", "items": { "type": "object" }, "default": [ { "sourceId": "sample-ai-ready-site", "sourceUrl": "https://example.com", "targetPath": "/", "robotsTxt": "User-agent: *\nAllow: /\n\nUser-agent: GPTBot\nAllow: /\n\nUser-agent: ChatGPT-User\nAllow: /\n\nUser-agent: OAI-SearchBot\nAllow: /\n\nUser-agent: ClaudeBot\nAllow: /\n\nUser-agent: Claude-User\nAllow: /\n\nUser-agent: anthropic-ai\nAllow: /\n\nUser-agent: PerplexityBot\nAllow: /\n\nUser-agent: Google-Extended\nAllow: /\n\nUser-agent: GoogleOther\nAllow: /\n\nUser-agent: CCBot\nAllow: /\n\nUser-agent: Bytespider\nAllow: /\n\nUser-agent: Meta-ExternalAgent\nAllow: /\n\nSitemap: https://example.com/sitemap.xml", "llmsTxt": "# Example AI crawler guidance\n\nThis fixture represents a site that allows major AI crawlers and exposes a sitemap.", "headers": { "x-robots-tag": "index, follow" }, "html": "<!doctype html><html><head><title>Example</title><meta name=\"robots\" content=\"index, follow\"></head><body>Example</body></html>" } ] }, "urls": { "title": "URLs To Fetch", "type": "array", "description": "Optional site URLs to fetch only when fetchUrls is true. The actor fetches /robots.txt and /llms.txt with strict byte and timeout caps.", "items": { "type": "string" }, "default": [] }, "fetchUrls": { "title": "Fetch URLs", "type": "boolean", "description": "Fetch robots.txt and llms.txt over HTTP. Default is false to keep zero-config runs local, deterministic, and cheap.", "default": false }, "expectedAccess": { "title": "Expected AI Crawler Access", "enum": [ "allow", "block", "neutral" ], "type": "string", "description": "Use allow for AI crawler readiness checks, block for opt-out audits, or neutral for inventory-only reporting.", "default": "allow" }, "auditedAgents": { "title": "Audited Crawler Agents", "type": "array", "description": "Crawler user-agent tokens to evaluate against robots.txt.", "items": { "type": "string" }, "default": [ "GPTBot", "ChatGPT-User", "OAI-SearchBot", "ClaudeBot", "Claude-User", "anthropic-ai", "PerplexityBot", "Google-Extended", "GoogleOther", "CCBot", "Bytespider", "Meta-ExternalAgent", "Googlebot", "Bingbot" ] }, "comparePrevious": { "title": "Compare Previous Robots", "type": "boolean", "description": "Compare previousRobotsTxt against current robotsTxt when a previous snapshot is supplied.", "default": true }, "requireLlmsTxt": { "title": "Require llms.txt", "type": "boolean", "description": "Flag targets that do not include llms.txt content.", "default": false }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 250, "type": "integer", "description": "Alias for Max Targets/Maximum Records used by the Junipr actor baseline. When both are provided, actor-specific limits still apply.", "default": 25 }, "includeReport": { "title": "Include Report Artifacts", "type": "boolean", "description": "Write summary JSON, full result JSON, and Markdown report artifacts to the key-value store.", "default": true }, "maxTargets": { "title": "Max Targets", "minimum": 1, "maximum": 250, "type": "integer", "description": "Maximum robots or URL targets to audit.", "default": 25 }, "fetchTimeoutMs": { "title": "Fetch Timeout Milliseconds", "minimum": 1000, "maximum": 30000, "type": "integer", "description": "HTTP timeout for optional robots.txt and llms.txt fetches.", "default": 10000 }, "maxRobotsBytes": { "title": "Max Robots Bytes", "minimum": 1000, "maximum": 1000000, "type": "integer", "description": "Maximum bytes to read from a fetched robots.txt file.", "default": 200000 }, "maxChargeUsd": { "title": "Maximum Charge (USD)", "minimum": 0, "maximum": 1000, "type": "number", "description": "Hard local spending cap for actor-start, per-item, and report events. The actor stops before work or withholds uncharged output when the next event would exceed this amount.", "default": 10 }, "dryRun": { "title": "Dry Run", "type": "boolean", "description": "Validate input and write a dry-run summary without PPE charges or dataset output.", "default": false }, "debug": { "title": "Debug Logs", "type": "boolean", "description": "Enable debug logs.", "default": false } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for AI Crawler Policy Auditor from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: