---
canonical_url: "https://docs.composio.dev/toolkits/crawl4ai"
markdown_url: "https://docs.composio.dev/toolkits/crawl4ai.md"
product: "platform"
version: null
last_updated: null
---

# Crawl4AI

Crawl4AI Cloud provides web scraping and search, structured extraction, asynchronous crawl and recipe jobs, page monitoring, pricing and lead intelligence, and email verification.

- **Category:** ai web scraping
- **Auth:** API_KEY
- **Composio-managed OAuth available?** N/A
- **Tools:** 51
- **Triggers:** 0
- **Slug:** `CRAWL4AI`
- **Version:** 00000000_00

## Tools

### Answer Question

**Slug:** `CRAWL4AI_ANSWER_QUESTION`

Answer a question from web sources and return the answer with citations when available. This Crawl4AI endpoint is experimental.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `deep` | boolean | No | Use deeper answer generation when true. |
| `question` | string | Yes | Question to answer from web sources, up to 4,000 characters. |
| `schema_json` | string | No | Optional JSON-encoded JSON Schema for structured answer text. The value must be valid JSON and is sent as a query string. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Cancel Recipe Job

**Slug:** `CRAWL4AI_CANCEL_RECIPE_JOB`

Stop a running recipe job. The provider retains it in paused state and may report a pause reason and partial usage.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `job_id` | string | Yes | Running recipe job id returned by SUBMIT_RECIPE_JOB. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Cancel Site Crawl

**Slug:** `CRAWL4AI_CANCEL_SITE_CRAWL`

Stop a running site crawl job; the job ends in the paused state.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `job_id` | string | Yes | Running site crawl job identifier to cancel. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Read Monitor Changes

**Slug:** `CRAWL4AI_CONSUME_MONITOR_CHANGES`

Read the oldest new changes across monitors and mark the returned feed items as read. Without since, later calls start after consumed items; pass a prior cursor to replay. Requires confirm_mark_read=true; use agent to limit which agent's feed is consumed.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `wait` | integer | No | Seconds to wait for a new change when none is currently unread. |
| `agent` | string | No | Consume changes only for this agent label. |
| `limit` | integer | No | Maximum changes to consume. |
| `since` | string | No | Prior feed cursor to replay from; omit to consume current unread changes. |
| `confirm_mark_read` | boolean | Yes | Must be true after the user approves consuming this feed page. Returned changes are marked read, including when no agent filter is supplied. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Monitor

**Slug:** `CRAWL4AI_CREATE_MONITOR`

Create a page-change monitor, or return the existing equivalent monitor, that performs recurring credit-consuming checks until paused or deleted and can send configured notifications.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `url` | string | Yes | Public HTTP or HTTPS page URL to monitor. |
| `name` | string | No | Optional human-readable label for the monitor. |
| `agent` | string | No | Stable agent label, up to 64 letters, digits, dots, underscores, or hyphens. It is fixed when the monitor is created. |
| `every` | string | No | Check interval: 'auto' or a compact duration of at least four minutes, such as '4m', '15m', '1h', '1d', or '1w'. |
| `watch` | string | No | Natural-language description of the change to watch for. Omit or send an empty string to detect any real page change. |
| `notify` | object | No | Optional webhook, email, or agent-trigger delivery settings. |
| `region` | string ("eu" | "sin" | "us") | No | Region from which the page is fetched. Omit to use the API gate's region. |
| `schema` | object | No | Optional JSON Schema for custom structured data returned with each change. Fields absent from the page are returned as null. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Plan Checkout

**Slug:** `CRAWL4AI_CREATE_PLAN_CHECKOUT`

Create an account-specific Stripe checkout flow for a Crawl4AI paid plan. This only returns a checkout URL: it does not directly charge a card or start the plan. Open and pay the Stripe checkout URL to complete the subscription. Use GET_PRICES_AND_PLANS first for current plan names and prices.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `plan` | string | Yes | Paid plan name from GET_PRICES_AND_PLANS. This creates a Stripe checkout flow; it does not subscribe the account until checkout is paid. |
| `billing` | string | No | Set to 'year' for yearly billing. Omit for the documented monthly checkout flow. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Delete Monitor

**Slug:** `CRAWL4AI_DELETE_MONITOR`

Permanently delete one page-change monitor and its history. Use this for intentional removal and test cleanup.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `monitor_id` | string | Yes | Monitor id to permanently delete. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Estimate Cost

**Slug:** `CRAWL4AI_ESTIMATE_COST`

Estimate the minimum and maximum Crawl4AI credits for a proposed API request without running that request.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `request` | object | Yes | Relevant target-operation fields, such as {'url': 'https://example.com/'} for scrape. |
| `endpoint` | string | Yes | Target Crawl4AI operation name, such as scrape. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Extract Prices

**Slug:** `CRAWL4AI_EXTRACT_PRICES`

Read pricing pages for up to 20 site-and-country combinations and return documented plans, billing periods, add-ons, discounts, trials, and source quotes.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `sites` | array | Yes | One to 20 domains or full pricing-page URLs to read. |
| `country` | string | No | Optional two-letter country code used for every site. |
| `countries` | array | No | Optional list of up to five two-letter countries used for every site. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Extract Structured Data

**Slug:** `CRAWL4AI_EXTRACT_STRUCTURED_DATA`

Extract structured records from exactly one URL or supplied content using an instruction, a JSON Schema, or both.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `url` | string | No | Public HTTP or HTTPS page URL to fetch and extract from; provide exactly one of url or content. |
| `schema` | object | No | JSON Schema describing each desired result record; provide this, instruction, or both. |
| `content` | string | No | Text or page content to extract from; provide exactly one of content or url. |
| `example` | string | No | Optional example object or array showing the desired extracted output shape. |
| `instruction` | string | No | Natural-language extraction instructions; provide this, schema, or both. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Forget Email Verification

**Slug:** `CRAWL4AI_FORGET_EMAIL_VERIFICATION`

Request permanent removal of Crawl4AI's stored verification answer for one email. This destructive privacy operation is documented as returning 204, but the provider may currently reject it with HTTP 405.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `email` | string | Yes | Email address whose stored verification answer must be forgotten. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Billing Balance

**Slug:** `CRAWL4AI_GET_BILLING_BALANCE`

Return the connected account's current free-credit balance, allowance, plan, tier, card status, spending, and top-up balance. Ledger values can trail the exact response-header balance by about one minute.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Lead Company

**Slug:** `CRAWL4AI_GET_COMPANY`

Get one private-preview Lead company by domain, LinkedIn page, or an unambiguous name optionally narrowed by country.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `name` | string | No | Company name. Provide exactly this, domain, or linkedin; country may narrow it. |
| `domain` | string | No | Company domain. Provide exactly this, linkedin, or name. |
| `country` | string | No | Optional two-letter country code used only with name. |
| `linkedin` | string | No | Company LinkedIn page URL. Provide exactly this, domain, or name. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Email Verification Job

**Slug:** `CRAWL4AI_GET_EMAIL_VERIFICATION_JOB`

Get later results for a batch email verification job, including background retries.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `job_id` | integer | Yes | Verification job id returned by VERIFY_EMAILS. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Monitor

**Slug:** `CRAWL4AI_GET_MONITOR`

Return one page-change monitor's configuration, health, baseline, cost, and notification settings.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `monitor_id` | string | Yes | Monitor id returned by CREATE_MONITOR or LIST_MONITORS. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Monitor Version

**Slug:** `CRAWL4AI_GET_MONITOR_VERSION`

Download the page exactly as Crawl4AI captured it for monitor evidence, returned as a Markdown text file.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `monitor_id` | string | Yes | Monitor id from a change event's monitor field. |
| `version_id` | string | Yes | Captured version id from a change event evidence URL. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Lead Person

**Slug:** `CRAWL4AI_GET_PERSON`

Get one private-preview Lead person and held contact data by one documented lookup.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `name` | string | No | Person's name; requires domain. Use this pair instead of email or linkedin. |
| `email` | string | No | Exact email address. Provide exactly this, linkedin, or name with domain. |
| `domain` | string | No | Company domain; requires name. Use this pair instead of email or linkedin. |
| `linkedin` | string | No | Person's LinkedIn profile URL. Provide exactly this, email, or name with domain. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Lead Person Email

**Slug:** `CRAWL4AI_GET_PERSON_EMAIL`

Get private-preview personal contact data: one person's checked email by one documented lookup. Lead may construct and verify a likely address from the company pattern before answering.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `name` | string | No | Person's name; requires domain. Use this pair instead of email or linkedin. |
| `email` | string | No | Exact email address. Provide exactly this, linkedin, or name with domain. |
| `domain` | string | No | Company domain; requires name. Use this pair instead of email or linkedin. |
| `linkedin` | string | No | Person's LinkedIn profile URL. Provide exactly this, email, or name with domain. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Lead Person Phone

**Slug:** `CRAWL4AI_GET_PERSON_PHONE`

Get private-preview personal contact data: a person's direct and company phones by one documented lookup.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `name` | string | No | Person's name; requires domain. Use this pair instead of email or linkedin. |
| `email` | string | No | Exact email address. Provide exactly this, linkedin, or name with domain. |
| `domain` | string | No | Company domain; requires name. Use this pair instead of email or linkedin. |
| `linkedin` | string | No | Person's LinkedIn profile URL. Provide exactly this, email, or name with domain. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Price History

**Slug:** `CRAWL4AI_GET_PRICE_HISTORY`

Return up to 1,000 observed price changes for one domain and optional country, newest first.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `domain` | string | Yes | Domain whose observed pricing history should be returned. |
| `country` | string | No | Optional two-letter country code used to distinguish regional prices. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Prices and Plans

**Slug:** `CRAWL4AI_GET_PRICES_AND_PLANS`

Return Crawl4AI's current credit prices, effort levels, plans, allowances, and request limits from the authoritative live catalog.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Recipe Health

**Slug:** `CRAWL4AI_GET_RECIPE_HEALTH`

Get the latest regional health check and release stage for every recipe, keyed by its live catalog name.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Recipe Job

**Slug:** `CRAWL4AI_GET_RECIPE_JOB`

Get a recipe job's status, progress counts, pause reason, and usage.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `job_id` | string | Yes | Recipe job id returned by SUBMIT_RECIPE_JOB. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Recipe Job Results

**Slug:** `CRAWL4AI_GET_RECIPE_JOB_RESULTS`

Download a recipe job's result rows as an NDJSON file. Each line is one dynamic recipe output row with a sequence number.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `job_id` | string | Yes | Completed recipe job id returned by SUBMIT_RECIPE_JOB. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Scrape Job

**Slug:** `CRAWL4AI_GET_SCRAPE_JOB`

Return a scrape job's current status, URL counts, and credit usage, with optional per-URL detail.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `full` | boolean | No | Set true to include per-URL detail; the provider receives 1. |
| `job_id` | string | Yes | Scrape job identifier returned by SUBMIT_SCRAPE_JOB. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Scrape Job Results

**Slug:** `CRAWL4AI_GET_SCRAPE_JOB_RESULTS`

Download one page of up to 500 scrape job results as NDJSON; pass the next result offset explicitly to retrieve another page.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `after` | integer | No | Zero-based result offset; each response contains at most 500 rows. |
| `job_id` | string | Yes | Scrape job identifier returned by SUBMIT_SCRAPE_JOB. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get SERP

**Slug:** `CRAWL4AI_GET_SERP`

Return structured Google rankings through Crawl4AI's GET transport, including source selection and the fixed device, engine, and result-type controls. Use SEARCH_SERP for the streamlined POST request.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `page` | integer | No | Result page from 1 to 30, counted in steps of num. |
| `fresh` | boolean | No | Skip the cache when true; the provider receives 1 or 0. |
| `query` | string | Yes | Google search query, up to 512 characters. |
| `device` | string | No | Google device profile; desktop is currently supported. |
| `engine` | string | No | Search engine; google is currently supported. |
| `source` | string ("auto" | "google") | No | Use either live Google source automatically, or require the google source. |
| `country` | string | No | Two-letter country code used to localize results. |
| `language` | string | No | Google language code used for the result page. |
| `location` | string | No | City or region used to localize the result page. |
| `time_range` | string ("hour" | "day" | "week" | "month" | "year") | No | Optional past-period filter for Google results. |
| `result_type` | string | No | Result type; organic is currently supported. |
| `results_per_page` | integer | No | Results requested, from 10 to 100 in multiples of 10. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Site Crawl Job

**Slug:** `CRAWL4AI_GET_SITE_CRAWL_JOB`

Read a site crawl job's state, progress counts, completion deadline, usage, and pause reason when applicable.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `job_id` | string | Yes | Site crawl job identifier returned by Submit Site Crawl. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Site Crawl Results

**Slug:** `CRAWL4AI_GET_SITE_CRAWL_RESULTS`

Download one page of up to 500 site crawl result rows as NDJSON, optionally continuing after a previously returned sequence number.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `after` | integer | No | Return up to 500 result rows whose sequence number follows this value. |
| `job_id` | string | Yes | Site crawl job identifier returned by Submit Site Crawl. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Billing Topups

**Slug:** `CRAWL4AI_LIST_BILLING_TOPUPS`

List account payments and credit additions newest first, including receipt URLs, one cursor-controlled page at a time.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum top-up records to return on this page (1-100). |
| `cursor` | string | No | Continuation cursor returned as next_cursor by the previous call. Omit for the first page. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Lead Industries

**Slug:** `CRAWL4AI_LIST_LEAD_INDUSTRIES`

Return documented LinkedIn industry names or names closest to query words.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `query` | string | No | Words for which to return the closest LinkedIn industry names. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Monitor Events

**Slug:** `CRAWL4AI_LIST_MONITOR_EVENTS`

List one monitor's change and health timeline oldest first, including facts and links to captured evidence versions. This does not mark the feed read.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum timeline events to return. |
| `since` | string | No | ISO 8601 timestamp or Unix seconds after which to return events. |
| `monitor_id` | string | Yes | Monitor id returned by CREATE_MONITOR or LIST_MONITORS. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Monitors

**Slug:** `CRAWL4AI_LIST_MONITORS`

List the connected account's page-change monitors, optionally filtered by agent label.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `agent` | string | No | Return only monitors created with this agent label. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Recipes

**Slug:** `CRAWL4AI_LIST_RECIPES`

List the live ready-made scraper catalog, including each recipe's dynamic input schema, output fields, cost, stage, and health.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Purchase Extra Credits

**Slug:** `CRAWL4AI_PURCHASE_EXTRA_CREDITS`

Immediately charge the saved card for the connected account's paid Crawl4AI plan and add non-expiring extra credits. This is a real, irreversible card charge, not a checkout flow. Call only after the user explicitly approves the exact US-dollar amount and set confirm_charge=true.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `amount` | number | Yes | Amount in US dollars to charge to the saved plan card for extra credits ($10-$1,000). |
| `confirm_charge` | boolean | Yes | Must be true only after the user explicitly approves charging the saved card for exactly amount US dollars. This local confirmation is never sent to Crawl4AI. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Retry Scrape Job

**Slug:** `CRAWL4AI_RETRY_SCRAPE_JOB`

Re-run only the failed URLs in an existing scrape job.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `job_id` | string | Yes | Scrape job identifier whose failed URLs should be retried. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Run Recipe

**Slug:** `CRAWL4AI_RUN_RECIPE`

Run one synchronous catalog recipe with inputs that match its current schema. Job-only recipes and catalog inputs marked secret are rejected.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `inputs` | object | No | Recipe-specific input object matching the selected recipe's live catalog schema. |
| `recipe_name` | string | Yes | Recipe name from LIST_RECIPES. |
| `bypass_cache` | boolean | No | Request a fresh recipe run instead of a cached result. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Scan Site URLs

**Slug:** `CRAWL4AI_SCAN_SITE_URLS`

Discover a site's known public page URLs from sitemaps, its home page, Common Crawl, and optionally the Wayback Machine without crawling each URL.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `mode` | string ("fast" | "full") | No | Use fast sources only, or also query the Wayback Machine index. |
| `domain` | string | Yes | Site host to scan; a leading https:// is accepted and removed by Crawl4AI. |
| `include` | string | No | Optional path prefix or glob selecting URLs to keep. |
| `max_urls` | integer | No | Maximum rows to return; Crawl4AI caps values above 50,000 at 50,000. |
| `bypass_cache` | boolean | No | Run a new scan instead of reusing a matching scan cached for seven days. |
| `include_subdomains` | boolean | No | Also list URLs on subdomains of the requested domain. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Scrape Page

**Slug:** `CRAWL4AI_SCRAPE_PAGE`

Fetch one public web page and return its Markdown, HTML, and optional parsed links, media, metadata, or tables.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `url` | string | Yes | Public HTTP or HTTPS page URL to scrape. |
| `parse` | string | No | Set true to parse all supported structured page elements, false to skip parsing, or select links, media, metadata, and tables individually. |
| `proxy` | string ("standard" | "extra") | No | Proxy level to use for the fetch. |
| `engine` | string ("auto" | "browser-light" | "browser") | No | Rendering engine; use auto unless the page requires browser rendering. |
| `format` | string ("both" | "md" | "html") | No | Content formats to return: Markdown and HTML, Markdown only, or HTML only. |
| `country` | string | No | Optional two-letter country code for geographically routed fetching. |
| `bypass_cache` | boolean | No | Fetch fresh content instead of using a cached result. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Scrape Pages

**Slug:** `CRAWL4AI_SCRAPE_PAGES`

Scrape up to 50 public URLs with shared options and return a downloadable NDJSON file of completion rows followed by a final summary row.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `urls` | array | Yes | One to 50 public HTTP or HTTPS page URLs to scrape. |
| `parse` | string | No | Whether and which structured page elements to parse for every URL. |
| `proxy` | string ("standard" | "extra") | No | Proxy level to use for every fetch. |
| `engine` | string ("auto" | "browser-light" | "browser") | No | Rendering engine used for every URL. |
| `format` | string ("both" | "md" | "html") | No | Content formats to return for every URL. |
| `country` | string | No | Two-letter country code for geographically routed fetching. |
| `bypass_cache` | boolean | No | Fetch fresh content instead of cached results. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Search Lead Companies

**Slug:** `CRAWL4AI_SEARCH_COMPANIES`

Search private-preview Lead companies by documented company filters and optional description-ranking words, one provider-cursor page at a time.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `about` | string | No | Intent or topic used only to rank matches; it does not remove matches. |
| `limit` | integer | No | Records on this page. |
| `where` | object | No | Structured company filters for name, industry, country, city, domain, description words, technology, hiring system, mail provider, people/email availability, and matching exclusions. |
| `exclude` | object | No | Company filters that matching records must not satisfy. |
| `next_cursor` | string | No | Continuation cursor returned by the previous page; omit for the first page. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Search Lead People

**Slug:** `CRAWL4AI_SEARCH_PEOPLE`

Search private-preview Lead people by documented company and person filters. Results can contain personal contact data; people who exercised removal are excluded permanently. Returns one provider-cursor page at a time.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `about` | string | No | Intent or topic used only to rank matches; it does not remove matches. |
| `limit` | integer | No | Records on this page. |
| `where` | object | No | Structured filters with company fields (industry, country, city, domain) and person fields (role, seniority, department, title, skills, topics, languages, status, and email availability), plus matching exclusions. |
| `exclude` | object | No | Company and person filters that matching records must not satisfy. |
| `next_cursor` | string | No | Continuation cursor returned by the previous page; omit for the first page. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Search SERP

**Slug:** `CRAWL4AI_SEARCH_SERP`

Return structured Google result ranks and SERP blocks for a localized query and explicit result page.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `page` | integer | No | Result page from 1 to 30; request another page explicitly to continue. |
| `fresh` | boolean | No | Bypass cached SERP data when true. |
| `query` | string | Yes | Google search query, up to 512 characters. |
| `country` | string | No | Two-letter country code used to localize results. |
| `language` | string | No | Language code used to localize results. |
| `location` | string | No | Geographic location name for localized results. |
| `time_range` | string ("hour" | "day" | "week" | "month" | "year") | No | Freshness window limiting results to the selected past period. |
| `results_per_page` | integer | No | Results requested, from 10 to 100 in multiples of 10. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Search Web

**Slug:** `CRAWL4AI_SEARCH_WEB`

Search the web for ranked, cleaned results, optionally including related questions, queries, news, videos, and discussions.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `query` | string | Yes | Search query, up to 512 characters. |
| `include_rich_results` | boolean | No | Include related questions, queries, entities, videos, news, and discussions when available. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Submit Recipe Job

**Slug:** `CRAWL4AI_SUBMIT_RECIPE_JOB`

Submit an asynchronous run for a job-capable recipe using its dynamic live catalog inputs. For execution-log safety, catalog inputs marked secret are intentionally unsupported and rejected before submission.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `inputs` | object | No | Recipe-specific input object matching the selected live catalog schema. |
| `recipe_name` | string | Yes | Job-capable recipe name from LIST_RECIPES. |
| `bypass_cache` | boolean | No | Request a fresh recipe run instead of a cached result. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Submit Scrape Job

**Slug:** `CRAWL4AI_SUBMIT_SCRAPE_JOB`

Submit up to 10,000 public URLs for asynchronous scraping and return a job identifier for status polling and paged result retrieval.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `urls` | array | Yes | One to 10,000 public HTTP or HTTPS page URLs to scrape. |
| `parse` | string | No | Whether and which structured page elements to parse for each URL. |
| `proxy` | string ("standard" | "extra") | No | Proxy level to use for each fetch. |
| `engine` | string ("auto" | "browser-light" | "browser") | No | Rendering engine to use for each URL. |
| `format` | string ("both" | "md" | "html") | No | Content formats to produce for each page. |
| `country` | string | No | Two-letter country code for geographically routed fetching. |
| `bypass_cache` | boolean | No | Fetch fresh content instead of cached results. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Submit Site Crawl

**Slug:** `CRAWL4AI_SUBMIT_SITE_CRAWL`

Start a background crawl of public pages within one site and return the job identifier used to inspect its status and results.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `url` | string | Yes | Public HTTP or HTTPS start page to crawl. |
| `depth` | integer | No | Number of link levels to follow below the start page, from zero to five. |
| `content` | string ("md" | "html" | "none") | No | Page content included in result rows: Markdown, HTML, or no body content. |
| `exclude` | string | No | Optional path prefix or glob selecting URLs never to follow. |
| `include` | string | No | Optional path prefix or glob selecting URLs to follow. |
| `max_pages` | integer | No | Maximum pages to fetch; Crawl4AI caps values above 500 at 500. |
| `include_subdomains` | boolean | No | Also follow links on subdomains of the start page's host. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Update Monitor

**Slug:** `CRAWL4AI_UPDATE_MONITOR`

Change a monitor's watch rule, schedule, notifications, schema, name, or paused state. At least one change must be supplied.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `name` | string | No | Replacement human-readable monitor name. |
| `every` | string | No | Replacement check interval: auto or a supported interval of at least four minutes. |
| `watch` | string | No | Replacement natural-language change rule. |
| `notify` | object | No | Replacement notification configuration, or null to clear it. |
| `paused` | boolean | No | Pause the monitor when true or resume it when false. |
| `schema` | object | No | Replacement JSON Schema for custom change data, or null to clear it. |
| `monitor_id` | string | Yes | Monitor id to update. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Verify Email

**Slug:** `CRAWL4AI_VERIFY_EMAIL`

Check whether one email can receive mail. Crawl4AI performs an SMTP conversation but sends no mail; stored answers may be reused for 30 days.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `email` | string | Yes | Email address to check without sending mail. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Verify Email Domain

**Slug:** `CRAWL4AI_VERIFY_EMAIL_DOMAIN`

Check one domain's mail acceptance, provider, gateway, catch-all, SPF, and DMARC results.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `domain` | string | Yes | Mail domain to check. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Verify Emails

**Slug:** `CRAWL4AI_VERIFY_EMAILS`

Check one to 1,000 email addresses without sending mail. Greylisted addresses return unknown initially and are retried in the background.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `emails` | array | Yes | One to 1,000 email addresses to check without sending mail. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |
