Bright Data

Agents & Workflows curated

The entry point to all Bright Data skills - start here, and it guides the agent to the right skill for the task at hand - web data and scraping, fetching or unblocking a page, search, browser automation, and the CLI, SDK and MCP surfaces. Use when Bright Data is not set up or stops authenticating - the CLI is missing ("bdata is not recognized"), login is needed or fails ("No API key found"), there is no Bright Data account yet and one must be created without a browser, a call is refused with 401, 407 or another auth error, an expected zone like cli_unlocker is missing, a key must be set in a project's .env, CI, or a container (BRIGHTDATA_API_KEY), or the user asks to install Bright Data, log in, get started, or which skill fits their task. Auth for every other Bright Data skill lives here.

Risky patterns

billing

Use when the question is about money on a Bright Data account: current balance, credit left, what was charged, spend or cost history, credits or free tier used, cost per zone, product or dataset, or what a job will cost before it runs. Read-only, and it never buys or changes anything. Not scraping or extraction (use scrape), not how to drive the CLI itself (use brightdata-cli), not a refused or failing call (use agent-onboarding).

brightdata-cli

Runs Bright Data jobs from a terminal with the bdata CLI, the published npm package @brightdata/cli. Use when the agent itself needs to run a Bright Data job from a shell right now, when it is building or testing a scraper, when a quick one-off check of a page, a search, a zone or a bill is enough, or when the user names bdata, brightdata, or the Bright Data CLI. Not for deterministic code that repeats the same job on a schedule, which belongs to brightdata-sdk. Not for an AI app that picks its tools at run time, which belongs to brightdata-mcp. Not for a first-time install or a login that will not go through, which belongs to agent-onboarding.

Data & Databases curated

brightdata-mcp

Agents & Workflows curated

Bright Data's MCP server, the tool layer that gives an LLM agent live web access with no shell. Use when wiring Bright Data tools into an AI app or agent framework that picks its tools at run time, when connecting Claude, Cursor, or another MCP client to Bright Data, when choosing which MCP tools or groups to turn on, or when the user says MCP. Covers the Remote server hosted at mcp.brightdata.com and the Local self-hosted @brightdata/mcp package, and which tool each job should route to. Not for the agent doing the job itself from a shell, which is brightdata-cli. Not for fixed repeated code in an app, which is brightdata-sdk. Not for install or auth problems, which is agent-onboarding.

brightdata-sdk

Bright Data's Python and Node.js SDKs for calling Web Scraper API, SERP, Web Unlocker and Scraper Studio from application code. Use when the user is writing code they keep that calls Bright Data on a schedule or inside a pipeline, when the same job runs again and again, when a Bright Data package is imported in Python or Node.js, when the user wants their own API or service built on top of Bright Data ("build me a scraper API", "wrap this in an endpoint"), or when the user names the SDK. Not for one-off checks typed at a shell, which belong to brightdata-cli. Not for an AI app that chooses its tools at run time, which belongs to brightdata-mcp. Not for install, login or API key problems, which belong to agent-onboarding.

Development curated

browser

Use when the user already has browser automation and wants it unblocked or run in the cloud: Playwright, Puppeteer, Selenium or another driver, a headless script that gets blocked, detected, or rate limited locally, or a computer-use AI that clicks by itself and needs somewhere to click. Also for asks that name CDP, connectOverCDP, browserWSEndpoint, a remote WebDriver, a websocket browser endpoint, or Browser API. Not for building the scraper for them (use scrape), not for one page as markdown, HTML, or a screenshot (use fetch), not for a search query (use search).

datasets

Use when the data is already collected and sold as a download, a huge generic corpus needed once where a few months old is fine ("every US company with more than 50 staff", a one-time training set). Also when the user holds a dataset_id that turns out to be a marketplace row, or asks what a ready dataset costs. Not for fresh, specific, or recurring collection, which is scraping and belongs to the scrape skill.

fetch

Use when the user wants one known URL returned as content: "get me this page", read this article, this page as markdown, save the raw HTML, screenshot this page, or page text for a RAG index or model context. Also when a plain fetch of a URL came back blocked or challenged instead of the real page: a 403 or another error status, a CAPTCHA, a bot wall, or an empty body. Wraps Bright Data Web Unlocker, so a blocked page still comes back. Not records or many pages of data from a site (use scrape), not a search query with no URL (use search), not driving a browser with your own Playwright, Puppeteer or Selenium code (use browser), not cost or credits (use billing), not auth or KYC failures (use agent-onboarding).