GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Bright Data Docs home page
  • Support
  • Documentation
  • API reference
  • Integrations
  • Account Management
  • For humans
  • For your coding agent
  • Choose a product
  • Python SDK
  • JavaScript SDK
  • Media Data API
  • Overview
  • How it works

This view

  • Original page
  • New address

GeezerVison is showing docs.brightdata.com — Bright Data for your coding agent - Bright Data Docs

Get structured data out of the Bright Data Scraper API from inside Claude Code, Cursor or Codex. Paste this in:

Read https://docs.brightdata.com/llms.txt, then use the Bright Data Scraper API to scrape https://www.amazon.com/dp/B0FQFB8FMG and show me the title, price and rating.

The agent reads the documentation index, installs what it needs and returns the record. To run the same thing yourself, or to see what it installed, start below.

​
Get your first Scraper API result

Two commands to structured JSON from the Bright Data Scraper API. Same result as the human quickstart, driven from the terminal.
1

Install and authenticate

npm i -g @brightdata/cli
bdata login
bdata login opens a browser to authorize, so you never paste a key. Use bdata login --device over SSH or in any headless environment.If a global install is blocked on your machine, run each command through npx instead:
npx -p @brightdata/cli bdata login
Keep the -p @brightdata/cli part. npx does not put bdata on your PATH, so every command needs the prefix, and the short npx bdata resolves to an unrelated package on npm rather than the Bright Data CLI.
2

Scrape a page

bdata pipelines run gd_l7q7dkf244hwjntr0 collect_by_url "https://www.amazon.com/dp/B0FQFB8FMG" --pretty
gd_l7q7dkf244hwjntr0 is the dataset_id of the Amazon products scraper, and collect_by_url returns one record per URL. You should see the product JSON printed. Processing time varies with target-site conditions and scraper workload. The CLI prints the run’s snapshot_id first and waits up to 600 seconds (--timeout) for the records. If you stop waiting, fetch them later with bdata pipelines results <snapshot_id>.
[
  {
    "title": "Apple AirPods Pro 3 Wireless Earbuds with Active Noise Cancellation",
    "asin": "B0FQFB8FMG",
    "brand": "Apple",
    "final_price": 199.99,
    "currency": "USD",
    "rating": 4.4,
    "reviews_count": 14411
  }
]
The full record carries 67 fields. Run bdata pipelines search <site or data type> to find a scraper for another site.
Install the agent skills and the agent reaches for these commands itself: 
npx skills add brightdata/skills
Then ask in plain language instead of typing the CLI:
Prompt
Scrape https://www.amazon.com/dp/B0FQFB8FMG and tell me the price and rating.

​
How do I scrape a different site?

Find the scraper with bdata pipelines search, then run it with its dataset_id. The search returns dataset_id, name, domain and collection_methods for each match. For LinkedIn people profiles: 
bdata pipelines search linkedin profiles
bdata pipelines run gd_l1viktl72bvl7bjuj0 collect_by_url "https://www.linkedin.com/in/satyanadella" --pretty
The same three steps work for any of the thousands of pre-built scrapers: 
bdata pipelines search <site or data type>
bdata pipelines info <dataset_id> <method>
bdata pipelines run <dataset_id> <method> <url> --<field> <value>
info lists the method’s input fields, an example input and a ready-to-run command. collect_by_url returns one record per URL, and discover_by_* methods return many records per input. An unknown field or a missing required field stops the command before the run starts, so nothing is billed. Search engines are not pipelines. Use bdata search for Google, Bing and Yandex results, and bdata scrape for any page that has no pre-built scraper. With the skills installed you do not look up the scraper yourself. Ask for the data and the agent finds the matching scraper:
Prompt
Get me the follower count and recent posts for the Bright Data LinkedIn company page.

​
What the agent sets up

What it gives the agentHowSetup
Knows which Bright Data product to use, and how the APIs workllms.txtOne line in a prompt
Runs search, scraping and structured extraction through the Bright Data CLIAgent skillsOne command
Calls 32 web tools live from inside the agent’s tool loopBright Data MCPOne command
Drives scrapers, zones and a remote browser from the terminalBright Data CLIOne command
These are not alternatives. See how they fit together.

​
Prerequisites

  • A Bright Data account. A human can sign up in a browser, or the agent can create the account itself with the agent registration protocol. New accounts get 5,000 free credits every month, no credit card required
  • A coding agent with terminal access: Claude Code, Cursor, Codex or any of the 40+ agents the skills ecosystem supports

​
How do I give my agent the full documentation?

Point the agent at llms.txt, a structured index of every Bright Data documentation page following the llms.txt standard. Every entry links to the .md version of the page, so the agent reads clean markdown with no HTML to parse.
Prompt
Read https://docs.brightdata.com/llms.txt to understand the available Bright Data
products, then help me choose the right API for scraping Amazon product pages.
To make it permanent instead of per-prompt, save the index into your project so every session has it: 
mkdir -p .claude && curl -o .claude/brightdata-docs.txt https://docs.brightdata.com/llms.txt

mkdir -p .cursor/rules && curl -o .cursor/rules/brightdata.md https://docs.brightdata.com/llms.txt

curl -s https://docs.brightdata.com/llms.txt >> AGENTS.md
Two files are published. llms.txt is the index and is the right default for a live agent session. llms-full.txt is the entire documentation in one file, meant for RAG pipelines and long-context injection rather than interactive use.
The token-efficient pattern for agents: load llms.txt to see what exists, identify the relevant page, then fetch that page’s .md URL for the detail. Append .md to any documentation URL to get the markdown, for example /products/mcp-server/overview.md.
Prefer to have the agent query the docs live instead of loading a file? The Docs MCP exposes this documentation as searchable MCP resources, so the agent retrieves pages inside its own reasoning loop. It is a separate server from the Bright Data MCP below: the Docs MCP reads documentation, the Bright Data MCP reaches the live web. Building a retrieval pipeline rather than a live agent session? Use llms-full.txt, which is the complete documentation as one markdown file: 
import httpx
from langchain.text_splitter import MarkdownTextSplitter

docs = httpx.get("https://docs.brightdata.com/llms-full.txt").text
chunks = MarkdownTextSplitter(chunk_size=1000, chunk_overlap=100).create_documents([docs])
vectorstore.add_documents(chunks)
llms-full.txt is large. For a live agent session, load llms.txt first and fetch individual .md pages on demand instead. It uses far fewer tokens.

​
How do I install Bright Data skills?

Skills are reusable instruction sets defined in SKILL.md files that give your agent embedded Bright Data API knowledge and the commands to act on it through the Bright Data CLI. One command installs them and auto-detects which agents you have: 
npx skills add brightdata/skills
The skills call bdata directly, so the global install from step 1 is what makes them work. Without bdata on your PATH the skills’ command -v bdata check fails. Confirm the install landed: 
npx skills list
Each installed skill prints on its own line with its path and the agents it was linked into: 
Project Skills

search ./.agents/skills/search Agents: Codex, Cursor
An empty list means the install did not take. Re-run npx skills add brightdata/skills and answer the scope prompt. The bundle covers search, scraping, structured extraction, the SDKs, proxies, Scraper Studio and MCP orchestration. The ones you will reach for first:
SkillWhat it gives the agent
SearchGoogle, Bing and Yandex results as structured JSON. Runs on the SERP API
ScrapeAny webpage as clean markdown, with CAPTCHA solving and JavaScript rendering. Runs on the Web Unlocker API
Data FeedsStructured extraction from Amazon, LinkedIn, Instagram, TikTok, YouTube and more
Scraper StudioBuilds a custom scraper for a site with no pre-built one
Bright Data MCPOrchestrates the MCP tools in one integration
Best PracticesAPI selection guide, auth patterns and code examples in Python and JavaScript
Run npx skills add brightdata/skills --list for the current set. Once installed, the agent invokes them directly: 
bdata search "your query" --engine google --json --pretty
bdata scrape "https://example.com"
bdata pipelines run gd_l7q7dkf244hwjntr0 collect_by_url "https://www.amazon.com/dp/B0FQFB8FMG" --pretty

​
Install into a specific agent

  • Claude Code
  • Cursor
  • Codex
  • Every agent at once
  • Any other agent
npx skills add brightdata/skills -a claude-code
Skills land in .claude/skills/ in your project, or ~/.claude/skills/ with -g. Claude Code discovers them on the next session. Verify with npx skills list -a claude-code.
npx skills add brightdata/skills -a cursor
Skills land in .cursor/skills/. Cursor Composer picks them up automatically. Reference one in chat: Use the scrape skill to extract content from https://example.com.
npx skills add brightdata/skills -a codex
Skills land in .agents/skills/, the shared location Codex reads alongside AGENTS.md.
npx skills add brightdata/skills --all

# Non-interactive, for CI
npx skills add brightdata/skills --all -y
The CLI auto-detects every agent you have installed and distributes the files to each.
Each skill is plain markdown, so you can inject it into any system prompt or RAG index:
git clone https://github.com/brightdata/skills.git
cat skills/bright-data-best-practices/SKILL.md
Add -g to any command to install globally across projects.

​
Manage installed skills

npx skills list      # what is installed
npx skills check     # are there updates
npx skills update    # update to latest
npx skills remove brightdata/skills
Skills are part of the open agent skills ecosystem and work across 40+ coding agents. The source, including each SKILL.md and its runnable scripts, lives at github.com/brightdata/skills. New skills are added regularly, so star the repository to follow along.

​
How do I connect the Bright Data MCP server?

The Bright Data MCP server gives your agent live web access through 32 tools for search, scraping, structured extraction and browser automation. It runs on the Web Unlocker API, so every request handles proxy rotation, anti-bot challenges and CAPTCHA solving. Each snippet below puts an API key in an agent config file. Those files are commonly committed to version control, so treat the key as you would any other secret. To avoid a long-lived key in a file entirely, the server also accepts OAuth 2.1, where the user signs in through a browser. 
claude mcp add --transport sse brightdata "https://mcp.brightdata.com/sse?token=YOUR_API_KEY"

{
  "mcpServers": {
    "brightdata-mcp": {
      "command": "npx",
      "args": ["-y", "@brightdata/mcp"],
      "env": {
        "API_TOKEN": "YOUR_API_KEY"
      }
    }
  }
}

codex mcp add brightdata --env API_TOKEN=YOUR_API_KEY -- npx -y @brightdata/mcp
Then try it with a prompt like Extract the Bright Data overview section from LinkedIn.
Control token usage. Load only the tools you need with tool groups, for example groups=scrapers,browser, or name individual tools such as tools=run_scraper. A smaller tool list means a smaller context and more usable requests.
Two versions exist. The remote server is fully managed and needs no setup. The local server is self-hosted for on-premise or private cloud. See the MCP server overview for both, and the integration guides for other clients.

​
Should I use skills, MCP or both?

Skills and the CLI are the default pair. Skills carry the knowledge: which Bright Data product fits a task, how to authenticate, how to handle pagination and errors. The CLI executes. Neither costs a live request until the agent runs a command. The MCP server matters when an agent has no terminal. It exposes the same capabilities as tools inside the agent’s own loop, which is the only route for a hosted assistant or a client that cannot shell out. This page lists terminal access as a prerequisite, so MCP is optional here. Add it when you want live web access inside the tool loop rather than through a shell.

​
Frequently asked questions

Can an AI agent create a Bright Data account for a user?

Yes. An agent creates the account itself through the agent registration protocol, with no password and no signup form. The agent posts the user’s email address to the registration endpoint, the user reads back the 6-character code Bright Data emails them, and the claim endpoint returns an API key. Disposable addresses and plus-aliased addresses such as [email protected] are rejected, so use the user’s real mailbox.

What products does an agent-created account include?

An agent-created account gets the standard 5,000 free credits every month, shared across the Web Unlocker API, SERP API, Scraper API, Scraper Studio and, since September 1, 2026, the Browser API. See the free tier for what each product costs against that pool. Registration also grants a one-time $2 trial credit valid seven days and pre-creates three zones, agent_serp, agent_unlocker and agent_browser_api, so the first SERP API, Web Unlocker API or Browser API call runs with no setup. The API key it issues is read-only for billing and cannot create or edit zones.

Can an agent-created account use Residential proxies?

No. Residential proxies require a KYC-verified business account, and the agent registration protocol provisions non-KYC products only. The Bright Data agent registration protocol states it directly: “Residential proxies always require a KYC-verified business account (via the Control Panel).” A human has to verify the account in the Control Panel before Residential proxies work. Datacenter and ISP proxies sit outside the protocol too, which provisions no proxy networks at all.

Do I need to install anything globally?

No. npx skills add brightdata/skills and npx -y @brightdata/mcp both fetch on demand, so there is no global dependency to maintain. The Bright Data CLI can also run through npx: npx -p @brightdata/cli brightdata --version.

Does the MCP server use the same free tier?

Yes. The MCP server draws from the same account-level free tier of 5,000 credits per month, from a single shared pool, because it runs on the Web Unlocker API. On team accounts that pool is shared across all users in the account.

Does the MCP server need a username?

No. Both the remote and local MCP servers authenticate with your API key only. Usernames in the format brd-customer-{customer_id}-zone-{zone_name} are for native proxy access, not MCP. If a third-party tool asks for a username, leave it empty.

Which agents are supported?

Skills work across the 40+ agents in the open agent skills ecosystem, including Claude Code, Cursor and Codex. The MCP server works with any MCP-compatible client. llms.txt works with anything that can fetch a URL.

Can my agent build a scraper for a site with no pre-built scraper?

Yes. Give it a target URL and a sentence describing the fields you want, and the Bright Data CLI generates the scraper through Scraper Studio. Copy-pasteable prompts for the full build, run and self-heal loop are in Scraper Studio coding agent prompts.

​
Next steps

Choose a product

Match your target site to the right Bright Data product, then go straight to its first request.

Build a scraper with prompts

Copy-pasteable Claude Code, Cursor and Codex prompts that build, run and self-heal a scraper.

Bright Data CLI

Scrape, search, manage zones and control a remote browser from the terminal.

Was this page helpful?

You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.