Integration · Company data

Connect Claude & ChatGPT to Bright Data

Ask your AI to fetch a web page, run a ready-made scraper or pull a filtered slice of a marketplace dataset through Bright Data. It can list your zones, check your balance, bandwidth and zone costs, start background collections and download the results when they are ready. Scraping uses paid traffic or credit on your Bright Data account.

Connect Bright Data free

Free plan, no credit card. Takes about a minute.

Try asking

“Fetch this product page as markdown through our Web Unlocker zone.”
The AI sends the URL through the zone and returns the page in the format you asked for. This uses paid traffic.
“Which zones do we have active?”
It lists your active proxy, Web Unlocker, SERP and scraping zones.
“Is there a ready-made scraper for this domain?”
It lists the Web Scraper API scrapers for the domain with their dataset IDs.

What your AI can do

Scraping

Fetch pages through Web Unlocker or SERP zones, run ready-made scrapers and start background collections.

Datasets

List marketplace datasets, create filtered snapshots and download snapshots and results in batches.

Zones and account

See active zones and zone status, balance, pending charges, bandwidth usage and zone costs.

“Start a collection for these 50 product URLs and download the results when ready.”
It triggers a background collection, checks its progress by snapshot ID and downloads the results once it is ready.
“What is our balance, and what did the SERP zone cost this month?”
It reads your balance and pending charges, and the zone's costs for those dates.
“Filter a marketplace dataset to records where country is Denmark, at most 1,000 records.”
It creates a filtered snapshot of the dataset and downloads it when it is ready.

18 tools for Bright Data

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

cancel_collectionDeletesCancel a running collection by `snapshot_id`. Work already done may still be billed.
download_collection_resultsDownload the results of a finished collection by `snapshot_id`, optionally in batches with `batch_size` and `part`.
download_dataset_snapshotDownload a ready marketplace dataset snapshot by `snapshot_id`, optionally in batches with `batch_size` and `part`.
filter_marketplace_datasetChanges dataCreate a filtered snapshot of a marketplace dataset. Pass `body_dataset_id` and `filter` (field, operator, value), optional `body_records_limit`. Returns a snapshot ID.
get_account_balanceGet your Bright Data account balance and pending charges.
get_bandwidth_usageGet bandwidth usage statistics across your zones, optionally between `from` and `to`.
get_collection_progressCheck the status of a triggered collection by `snapshot_id` (running, ready or failed).
get_dataset_snapshotGet the status and details of a marketplace dataset snapshot by `snapshot_id`.
get_domain_success_rateGet the Web Unlocker success rate for a `domain`, such as example.com.
get_zone_costsGet the costs of one `zone`, optionally between `from` and `to` dates (YYYY-MM-DD).
get_zone_statusGet whether one `zone` is active or disabled.
list_active_zonesList your active zones (proxy, Web Unlocker, SERP and scraping products). Use to find a `zone` name.
list_collectionsList collection snapshots for a `dataset_id`, filtered by `status` and date range.
list_marketplace_datasetsList the datasets available in the Bright Data marketplace with their IDs.
list_scrapersList the ready-made Web Scraper API scrapers, optionally for one `domain`. Use to find a `dataset_id` for scraping.
scrape_urlChanges dataFetch a web page through a Web Unlocker or SERP zone. Pass `url`, `zone` and `format` (raw for HTML, json for structured); optional `country`, `data_format` (e.g. markdown) and `render`. Uses paid traffic.
scrape_with_scraperChanges dataRun a scraper right away and get results back. Pass `dataset_id` and `items` (list of inputs such as {"url": ...}). Uses paid credit.
trigger_collectionChanges dataStart a background data collection. Pass `dataset_id` and `items` (list of inputs such as {"url": ...}); optional `type` discover_new with `discover_by` and limits. Returns a snapshot ID. Uses paid credit.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose Bright Data from the app list.
2
Paste your key
Paste a Bright Data API key. In the Bright Data control panel, open Account settings > Users and API keys (brightdata.com/cp/setting/users). Copy the default API key or add a new one with the permissions you want.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Bright Data?

The AI can fetch web pages through Web Unlocker or SERP zones, run scrapers, start, check, download and cancel collections, and create, check and download filtered marketplace dataset snapshots. It can also list zones, scrapers and datasets, and read zone status, domain success rates, balance, bandwidth usage and zone costs.

Does the AI see my Bright Data API key?

No. Your Bright Data credentials are encrypted at rest and never shown to the AI. After you save them, they are not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start with account and zone lookups. Tools that spend traffic or credit, like scrape_url and trigger_collection, can require your approval before they run, and so can cancelling a collection. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You connect your own Bright Data account, so anything Bright Data charges is between you and Bright Data.

Does scraping cost extra?

Yes, on the Bright Data side. Fetching pages, running scrapers and starting collections use paid traffic or credit on your Bright Data account, and cancelling a collection may still bill work already done. The AI can check your balance, pending charges and zone costs at any time.