NagentArtefacts
Dev & Technology
Enterprise and White Glove
Company
Bright Data connects to a Nagent workspace with an API key. Once it is connected, agents can call 10 Bright Data actions, such as "Get Available Cities", "Get Available Countries" and "List Unlocker Zones". Nothing is enabled on connect: each action is allowed one at a time, and an action with side effects runs or waits for a person according to the agent's level.
Every operation an agent can call against Bright Data, with input parameters and output schema.
BRIGHTDATA_CRAWL_APITool to trigger an asynchronous site crawl job to extract content across multiple pages or entire domains. Returns a snapshot_id required by BRIGHTDATA_GET_SNAPSHOT_STATUS (poll until complete) and BRIGHTDATA_GET_SNAPSHOT_RESULTS (call only after completion; querying early yields empty or partial data). Use when you need to start a crawl for a given dataset and list of URLs. Large crawls can produce very large payloads — fetch results incrementally.
Input parameters
List of objects containing URLs or other parameters required by the crawler. Supports scope configuration fields such as depth limits, includePaths, and excludePaths to prevent over-crawling large sites, which increases cost and runtime.
Your dataset ID.
Whether to include an errors report with the results.
Pipe-separated list of output fields to include (e.g., 'url\\|about.updated_on').
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
BRIGHTDATA_DATASET_LISTTool to list all available pre-made scrapers (datasets) from Bright Data's marketplace. Use when you need to browse available data sources for structured scraping.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
BRIGHTDATA_FILTER_DATASETTool to apply custom filter criteria to a marketplace dataset (BETA). Use after selecting a dataset to generate a filtered snapshot.
Input parameters
Optional list of file paths to CSV or JSON files containing filter values.
Filter criteria object. Basic filter: {"name": "field_name", "operator": "=", "value": "search_term"}. Combine filters: {"operator": "and", "filters": \[{...}, {...}\]}. Supported operators: '=', '!=', '<', '<=', '>', '>=', 'in', 'not_in', 'includes', 'not_includes', 'array_includes', 'not_array_includes', 'is_null', 'is_not_null'. Max nesting depth: 3.
ID of the dataset to filter.
Optional maximum number of records to include in the snapshot, must be >= 1.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
BRIGHTDATA_GET_LIST_OF_AVAILABLE_CITIESTool to get available static network cities for a given country. Use when you need to configure static proxy endpoints after selecting a country.
Input parameters
ISO 3166-1 alpha-2 country code to list available cities for.
Type of static proxy pool. 'dc' for datacenter, 'static_res' for residential.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
BRIGHTDATA_GET_LIST_OF_AVAILABLE_COUNTRIESTool to list available countries and their ISO 3166-1 alpha-2 codes. Use when you need to configure zones with valid country codes before provisioning proxies.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
BRIGHTDATA_GET_SNAPSHOT_RESULTSTool to retrieve the scraped data from a completed crawl job by snapshot ID. Only call after confirming the job is complete via BRIGHTDATA_GET_SNAPSHOT_STATUS — querying before completion yields empty or partial data. Use after triggering a crawl or filtering a dataset to download the collected data.
Input parameters
Which batch part to download (starts from 1). Use with 'batch_size' parameter.
Desired output format. Options: json, csv, ndjson (newline-delimited JSON), or jsonl (JSON Lines).
Whether to compress the result using gzip.
Divide snapshot into batches of this size (minimum 1000 records). Use with 'part' parameter. For large snapshots, always paginate using both `batch_size` and `part` together; skipping pagination can silently drop records or exceed response limits.
Identifier of the snapshot to fetch results for. This is the snapshot_id returned by the Trigger Site Crawl (CRAWL_API) action, typically in the format 's_xxxxxxxxxxxxx'. IDs expire after some time; stale or invalid IDs return empty or error responses.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
BRIGHTDATA_GET_SNAPSHOT_STATUSTool to check the processing status of a crawl job using snapshot ID. Call before attempting to download results to ensure data collection is complete.
Input parameters
Identifier of the snapshot to check. This is the snapshot_id returned by the Trigger Site Crawl (CRAWL_API) action, typically in the format 's_xxxxxxxxxxxxx'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
BRIGHTDATA_LIST_WEB_UNLOCKER_ZONESTool to list your configured Web Unlocker zones and proxy endpoints. Use to view available zones for web scraping and bot protection bypass.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
BRIGHTDATA_SERP_SEARCHTool to perform SERP (Search Engine Results Page) searches across different search engines using Bright Data's SERP Scrape API. Use when you need to retrieve search results, trending topics, or competitive analysis data. This action submits an asynchronous request and returns a response ID for tracking.
Input parameters
Zone identifier for your SERP API product configuration. This is a required parameter that must be obtained from your Bright Data dashboard under 'Proxies & Scraping Infrastructure'. Each user has their own unique zone name.
Response format. 'json' returns structured data, 'raw' returns HTML string.
HTTP method for the request.
Two-letter ISO country code for proxy location and localized search results.
The search query keywords to execute.
Additional data transformation. 'markdown' converts HTML to clean markdown, 'screenshot' captures a PNG image.
Search engine to use for the query. Supported values: google, bing, yahoo, duckduckgo, yandex.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
BRIGHTDATA_WEB_UNLOCKERTool to bypass bot detection, captcha, and other anti-scraping measures to extract content from websites. Use when you need to scrape websites that block automated access or require JavaScript rendering. Some responses may still contain CAPTCHA challenge pages or incomplete HTML; inspect the response before retrying, and avoid aggressive retry loops.
Input parameters
The URL of the website to unlock and scrape.
Web Unlocker zone name (required, non-empty). Call BRIGHTDATA_LIST_WEB_UNLOCKER_ZONES first to get available zones.
Response format - 'raw' returns HTML content as string, 'json' returns structured data.
ISO 3166-1 alpha-2 country code for the proxy location (e.g., 'us', 'gb', 'de').
Set to 'markdown' to convert page content to markdown format.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
Agents can call 10 Bright Data actions on Nagent, including "Get Available Cities", "Get Available Countries" and "List Unlocker Zones". Get Available Cities: Get available static network cities for a given country. Each action is listed on this page with its input parameters and its output.
Bright Data connects with an API key, under your workspace's own connection. Nothing is enabled on connect: each action is allowed one at a time and can be scoped to the agents that need it.
Get Available Cities takes 1 required input: country. It also takes 1 optional input: pool_ip_type. It returns data, error and successful.