> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Anakin

> Anakin provides web scraping, crawling, search, browser automation, monitoring, and pre-built website actions for AI agents.

![Anakin logo](https://mintcdn.com/composio-preview/qzegrvAapILigeDI/images/toolkits/anakin_io.svg?fit=max\&auto=format\&n=qzegrvAapILigeDI\&q=85\&s=db88e76de86636324328a2e426ac5bdd)

* **Category:** web scraping & browser
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 26
* **Triggers:** 0
* **Slug:** `ANAKIN_IO`
* **Version:** 20261030\_00

## Tools

> [accordion] Create Monitor
>
> **Slug:** `ANAKIN_IO_CREATE_MONITOR`
>
> Create a recurring page or site monitor with optional structured extraction, browser rendering, and change alerts. Active scheduled checks consume credits.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> Absolute page or site URL to monitor.
>
> **scope** `string ("page" | "site")`
>
> Monitor one page or crawl a site for changes.
>
> **ai\_goal** `string`
>
> Natural-language guidance for changes that matter when AI mode is enabled.
>
> **ai\_mode** `boolean`
>
> Use AI to filter trivial changes and summarize meaningful ones.
>
> **country** `string`
>
> Lowercase ISO alpha-2 proxy country code.
>
> **is\_active** `boolean`
>
> Start scheduled checks immediately rather than creating a paused monitor.
>
> **max\_depth** `number`
>
> Maximum link depth for a site monitor (1-5).
>
> **max\_pages** `number`
>
> Maximum number of organically discovered pages per site-monitor run.
>
> **expires\_at** `string`
>
> Future ISO 8601 timestamp or YYYY-MM-DD date when monitoring stops.
>
> **session\_id** `string`
>
> Saved browser session ID for monitoring authenticated pages.
>
> **watch\_mode** `string ("full_page" | "specific_data")`
>
> Detect changes across the full page or in structured extracted data.
>
> **use\_browser** `boolean`
>
> Render pages in a browser for JavaScript-heavy sites.
>
> **alert\_emails** `string`
>
> Comma-separated email recipients for change alerts.
>
> **watch\_format** `string ("markdown" | "html" | "cleaned_html")`
>
> Page content format compared when watch\_mode is full\_page.
>
> **output\_schema** `object`
>
> JSON Schema of fields to extract; required when watch\_mode is specific\_data.
>
> **exclude\_patterns** `array`
>
> URL path globs to exclude from a site monitor.
>
> **include\_patterns** `array`
>
> Full URLs to pin or path globs to include in a site monitor.
>
> **interval\_minutes** `number` *required*
>
> Minutes between checks; the minimum is 15.
>
> **alert\_webhook\_url** `string`
>
> HTTPS endpoint notified when the monitor detects a change.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Monitor
>
> **Slug:** `ANAKIN_IO_DELETE_MONITOR`
>
> Permanently delete a monitor and all of its retained history. Use only for explicit cleanup because this action is destructive and cannot be undone.
>
> #### Input Parameters
>
> **monitor\_id** `string` *required*
>
> Monitor ID to permanently delete, including its retained history.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Execute Wire Action
>
> **Slug:** `ANAKIN_IO_EXECUTE_WIRE_ACTION`
>
> Start a parameterized asynchronous Wire action by action ID, optionally using an existing target-site credential, and return a job ID. The selected action may read, create, update, submit, or delete target-site data, and its execution consumes the advertised credits.
>
> #### Input Parameters
>
> **params** `object`
>
> Action-specific parameters matching the selected Wire action's dynamic schema.
>
> **action\_id** `string` *required*
>
> Wire action ID returned by Resolve Wire Actions or Get Wire Catalog.
>
> **webhook\_url** `string`
>
> Optional HTTPS callback URL for completion notification.
>
> **credential\_id** `string`
>
> Existing target-site credential ID when the selected action requires authentication.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Agentic Search
>
> **Slug:** `ANAKIN_IO_GET_AGENTIC_SEARCH`
>
> Check an agentic research job and return its generated summary and structured data when complete.
>
> #### Input Parameters
>
> **job\_id** `string` *required*
>
> Agentic search job ID returned by Start Agentic Search.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get AI Visibility Search
>
> **Slug:** `ANAKIN_IO_GET_AI_VISIBILITY_SEARCH`
>
> Check an AI visibility search and return its synthesis plus each engine's answer, verdict, latency, credit use, or error.
>
> #### Input Parameters
>
> **search\_id** `string` *required*
>
> AI visibility search ID returned by Start AI Visibility Search.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Crawl
>
> **Slug:** `ANAKIN_IO_GET_CRAWL`
>
> Check a crawl job and return page content, progress, timing, and errors.
>
> #### Input Parameters
>
> **job\_id** `string` *required*
>
> Crawl job ID returned by Start Crawl.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Monitor
>
> **Slug:** `ANAKIN_IO_GET_MONITOR`
>
> Get one monitor's current configuration, schedule, and state by ID.
>
> #### Input Parameters
>
> **monitor\_id** `string` *required*
>
> Monitor ID returned by Create Monitor or List Monitors.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Monitor Snapshot Content
>
> **Slug:** `ANAKIN_IO_GET_MONITOR_SNAPSHOT_CONTENT`
>
> Fetch the stored full-page content for a monitor snapshot identified by a detected change.
>
> #### Input Parameters
>
> **monitor\_id** `string` *required*
>
> Monitor ID that owns the snapshot.
>
> **snapshot\_id** `string` *required*
>
> Snapshot ID returned by List Monitor Changes.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Scrape Job
>
> **Slug:** `ANAKIN_IO_GET_SCRAPE_JOB`
>
> Check a single or batch scrape job and return requested content or per-URL results when complete.
>
> #### Input Parameters
>
> **job\_id** `string` *required*
>
> Scrape job ID returned by Scrape URL after a timeout or by Start Batch Scrape.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Site Map
>
> **Slug:** `ANAKIN_IO_GET_SITE_MAP`
>
> Check a site-map job and return discovered internal and external links with timing and errors.
>
> #### Input Parameters
>
> **job\_id** `string` *required*
>
> Site-map job ID returned by Start Site Map.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Wire Catalog
>
> **Slug:** `ANAKIN_IO_GET_WIRE_CATALOG`
>
> Get one Wire website catalog with its executable actions, dynamic parameter schemas, authentication modes, and credit costs.
>
> #### Input Parameters
>
> **catalog\_slug** `string` *required*
>
> Wire catalog slug returned by Resolve Wire Actions.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Wire Job
>
> **Slug:** `ANAKIN_IO_GET_WIRE_JOB`
>
> Check a Wire job and return processing guidance, completed structured data or file metadata, credit use, execution time, or failure details.
>
> #### Input Parameters
>
> **job\_id** `string` *required*
>
> Wire job ID returned by Execute Wire Action.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List AI Visibility Sources
>
> **Slug:** `ANAKIN_IO_LIST_AI_VISIBILITY_SOURCES`
>
> List the AI engine slugs currently available for AI visibility searches.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Monitor Changes
>
> **Slug:** `ANAKIN_IO_LIST_MONITOR_CHANGES`
>
> List up to 200 recent detected changes for a monitor, newest first, including snapshot IDs and structured diffs.
>
> #### Input Parameters
>
> **monitor\_id** `string` *required*
>
> Monitor ID whose detected changes should be listed.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Monitors
>
> **Slug:** `ANAKIN_IO_LIST_MONITORS`
>
> List all monitors owned by the connected account with their schedules, state, and configuration.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Wire Jobs
>
> **Slug:** `ANAKIN_IO_LIST_WIRE_JOBS`
>
> List Wire execution history one page at a time, including job status and summary statistics when available.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Number of Wire jobs to return in this page.
>
> **next\_cursor** `string`
>
> Continuation cursor returned by a previous call; omit for the first page.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Resolve Wire Actions
>
> **Slug:** `ANAKIN_IO_RESOLVE_WIRE_ACTIONS`
>
> Find Wire actions by intent and optional catalog, category, or authentication filters, including required parameters and credit cost.
>
> #### Input Parameters
>
> **query** `string` *required*
>
> Natural-language capability or task to find.
>
> **catalog** `string`
>
> Restrict matches to one Wire catalog slug.
>
> **category** `string`
>
> Restrict matches to a Wire catalog category.
>
> **auth\_mode** `string ("none" | "optional" | "required")`
>
> Restrict matches by target-site authentication requirement.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Run Monitor Now
>
> **Slug:** `ANAKIN_IO_RUN_MONITOR_NOW`
>
> Queue an immediate check for an existing monitor; the run may consume credits.
>
> #### Input Parameters
>
> **monitor\_id** `string` *required*
>
> Monitor ID to check immediately.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Scrape URL
>
> **Slug:** `ANAKIN_IO_SCRAPE_URL`
>
> Scrape one URL synchronously when possible, optionally using a browser, extraction schema, saved session, or page actions. Browser actions can click, type, or press keys and may modify an authenticated target site. A timed-out call returns a non-terminal job ID for Get Scrape Job. The scrape may consume credits.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> Absolute HTTP or HTTPS URL to scrape.
>
> **actions** `array`
>
> Ordered browser actions to run before extraction (maximum 15). Click, write, and press actions may modify the target site, especially when session\_id supplies an authenticated session.
>
> **country** `string`
>
> Lowercase ISO alpha-2 proxy country code.
>
> **formats** `array`
>
> Outputs to produce. When omitted, Anakin returns markdown, HTML, and cleaned HTML.
>
> **session\_id** `string`
>
> Saved browser session ID to use for authenticated pages.
>
> **use\_browser** `boolean`
>
> Use browser rendering for JavaScript-heavy pages.
>
> **webhook\_url** `string`
>
> Optional HTTPS callback URL for completion notification.
>
> **generate\_json** `boolean`
>
> Generate structured JSON from the scraped page.
>
> **output\_schema** `object`
>
> JSON Schema describing fields to extract; this implies JSON generation.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Search Web
>
> **Slug:** `ANAKIN_IO_SEARCH_WEB`
>
> Run a synchronous AI-powered web search and return ranked pages with titles, snippets, and dates. The search consumes credits.
>
> #### Input Parameters
>
> **limit** `number`
>
> Maximum number of search results to return (1-20).
>
> **query** `string` *required*
>
> Natural-language web search query.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Set Monitor State
>
> **Slug:** `ANAKIN_IO_SET_MONITOR_STATE`
>
> Pause or resume a monitor; resuming can optionally set a new expiration time.
>
> #### Input Parameters
>
> **state** `string ("paused" | "active")` *required*
>
> Desired monitor state: paused stops scheduled checks and active resumes them.
>
> **expires\_at** `string`
>
> Optional future ISO 8601 timestamp or YYYY-MM-DD date for the resumed monitor. Omit to resume without an end date.
>
> **monitor\_id** `string` *required*
>
> Monitor ID to pause or resume.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Start Agentic Search
>
> **Slug:** `ANAKIN_IO_START_AGENTIC_SEARCH`
>
> Start a multi-stage web research job from a natural-language prompt and return its job ID for status checks. The research job consumes credits.
>
> #### Input Parameters
>
> **prompt** `string` *required*
>
> Research question or task for the agentic search.
>
> **webhook\_url** `string`
>
> Optional HTTPS callback URL for completion notification.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Start AI Visibility Search
>
> **Slug:** `ANAKIN_IO_START_AI_VISIBILITY_SEARCH`
>
> Ask selected AI engines a query and return a search ID for collecting per-engine answers and synthesis. Each selected engine may consume credits.
>
> #### Input Parameters
>
> **query** `string` *required*
>
> Question to send to the selected AI engines (maximum 2,000 characters).
>
> **country** `string`
>
> Lowercase ISO alpha-2 country code used to localize results.
>
> **sources** `array`
>
> AI engine slugs to query; omit to use the provider default set.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Start Batch Scrape
>
> **Slug:** `ANAKIN_IO_START_BATCH_SCRAPE`
>
> Start a parallel scrape of 1-10 URLs and return a job ID for Get Scrape Job. Each URL may consume credits.
>
> #### Input Parameters
>
> **urls** `array` *required*
>
> One to ten absolute HTTP or HTTPS URLs to scrape.
>
> **country** `string`
>
> Lowercase ISO alpha-2 proxy country code.
>
> **session\_id** `string`
>
> Saved browser session ID to use for authenticated pages.
>
> **use\_browser** `boolean`
>
> Use browser rendering for JavaScript-heavy pages.
>
> **webhook\_url** `string`
>
> Optional HTTPS callback URL for completion notification.
>
> **generate\_json** `boolean`
>
> Generate structured JSON for each URL.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Start Crawl
>
> **Slug:** `ANAKIN_IO_START_CRAWL`
>
> Start a bounded multi-page crawl and return a job ID for Get Crawl. Crawled pages may consume credits.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> Absolute starting URL to crawl.
>
> **depth** `number`
>
> Maximum link depth from the starting URL (1-5).
>
> **country** `string`
>
> Lowercase ISO alpha-2 proxy country code.
>
> **max\_pages** `number`
>
> Maximum pages to crawl (1-100).
>
> **session\_id** `string`
>
> Saved browser session ID for authenticated pages.
>
> **use\_browser** `boolean`
>
> Use browser rendering for JavaScript-heavy pages.
>
> **webhook\_url** `string`
>
> Optional HTTPS callback URL for completion notification.
>
> **exclude\_patterns** `array`
>
> URL patterns to exclude from the crawl.
>
> **include\_patterns** `array`
>
> URL patterns that pages must match.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Start Site Map
>
> **Slug:** `ANAKIN_IO_START_SITE_MAP`
>
> Start a bounded site link-discovery job and return a job ID for Get Site Map. The job may consume credits.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> Absolute starting URL whose links should be discovered.
>
> **depth** `number`
>
> Maximum discovery depth (1-5).
>
> **limit** `number`
>
> Maximum total links to return (1-5,000).
>
> **search** `string`
>
> Optional text that discovered links must match.
>
> **session\_id** `string`
>
> Saved browser session ID for authenticated sites.
>
> **use\_browser** `boolean`
>
> Use browser rendering for JavaScript-generated links.
>
> **webhook\_url** `string`
>
> Optional HTTPS callback URL for completion notification.
>
> **limit\_per\_level** `number`
>
> Maximum links retained at each depth level (1-500).
>
> **include\_subdomains** `boolean`
>
> Include links on subdomains.
>
> **include\_external\_links** `boolean`
>
> Include links outside the starting site's domain.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
