Get started

Bright Data for AI agents

Bright Data is a web data platform that businesses use to scrape protected sites, pull search engine results, and run large-scale data collection jobs. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect Bright DataSee the 22 actions ↓
Web data and scrapingAPI keyMCP + RESTbrightdata.com
AUDIT LOG · BRIGHT DATAPOLICY: acme-support
09:41:07 · claude · u_8f2read
bright_data.list_scrapers
List Scraper Studio Scrapers✓ allowed · 212ms
09:41:08 · claude · u_8f2read
bright_data.crawl_api
Start Site Crawl✓ allowed · 164ms
09:41:09 · claude · u_8f2write
bright_data.create_safe_zone
Create Safe Zone✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
bright_data.search_web_archive
Search Web Archive✕ blocked · policy: deny
EVERY BRIGHT DATA CALL, ON THE RECORD
01 · USE CASES

What agents do in Bright Data.

01

Check zone cost and bandwidth

Read-only lookup of a proxy zone's bandwidth use and cost before running another scrape.

02

Scrape a protected page

Scrape a protected URL or run a SERP search after the user confirms the target and cost.

03

Require approval before a site crawl

Treat starting a full site crawl as needing confirmation since it can consume significant data credits.

02 · ACTIONS

22 Bright Data actions, graded by risk.

Every Bright Data action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

14

Look things up. Allowed by default.

  • bright_data.get_zone_cost
    Get Zone Cost
  • bright_data.list_scrapers
    List Scraper Studio Scrapers
  • bright_data.get_serp_results
    Get SERP Results
  • bright_data.get_zone_bandwidth
    Get Zone Bandwidth
  • bright_data.get_snapshot_status
    Check Snapshot Status
  • bright_data.get_customer_balance
    Get Customer Balance
  • bright_data.get_snapshot_results
    Download Snapshot Results
  • bright_data.get_deep_lookup_status
    Get Deep Lookup Status
  • bright_data.get_deep_lookup_results
    Get Deep Lookup Results
  • bright_data.list_web_unlocker_zones
    List Unlocker Zones
  • bright_data.get_list_of_available_cities
    List Available Cities
  • bright_data.get_list_of_available_countries
    List Available Countries
  • bright_data.crawl_api
    Start Site Crawl
  • bright_data.scrape_data_sync
    Scrape Data Synchronously

write

6

Create and change things. Allow, or ask the user first.

  • bright_data.create_safe_zone
    Create Safe Zone
  • bright_data.serp_search
    Search SERP
  • bright_data.dataset_list
    List Marketplace Datasets
  • bright_data.web_unlocker
    Scrape Protected URL
  • bright_data.filter_dataset
    Filter Dataset
  • bright_data.start_deep_lookup
    Start Deep Lookup

destructive

2

Delete, cancel or archive. Ask first, or deny outright.

  • bright_data.search_web_archive
    Search Web Archive
  • bright_data.get_web_archive_search
    Get Web Archive Search
03 · HOW IT WORKS

Bright Data in three steps.

  1. 01Your users connect Bright DataThey add their Bright Data api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Safe Zone” can wait for the user, and “search Web Archive” can be denied outright.
  3. 03Any agent can actYour agent calls Bright Data through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('bright_data', {
  read: 'allow',
  write: 'ask',        // create_safe_zone
  destructive: 'deny',  // search_web_archive
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Bright Data connects.

Users add their Bright Data api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Bright Data connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Bright Data from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More web data and scraping apps.

Firecrawl30 actionsTavily5 actionsExa20 actionsAgentql3 actionsAgenty79 actionsAirtop10 actionsJust One API288 actionsApify183 actions
ALL WEB DATA AND SCRAPING APPS →
07 · FAQ

Bright Data and Arc0, answered.

Q01

Can I use Bright Data with Claude, ChatGPT or Cursor?

Yes. Connect Bright Data to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Bright Data actions you allow.

Q02

How do users connect Bright Data?

Users add their Bright Data api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Bright Data actions can my agent take?

22 in total: 14 read, 6 write and 2 destructive, such as “create Safe Zone”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Bright Data?

Yes. Actions like “search Web Archive” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Bright Data too?

Yes. The same Bright Data connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Bright Data into your agent.

Your users connect Bright Data once, under your brand. Your agent gets 22 actions behind your policies, with every call on the record.

Connect Bright DataBrowse all apps →

Free to build · MCP + REST · Audit log on every plan