# Bright Data — how to use (mcp.ai)

Connect your Bright Data account and use 10 tools for web scraping straight from your AI agent. Connect with your own API key. Bright Data provides the world's #1 web data platform with Web Unlocker for bypassing anti-bot systems, SERP API for search engine data, and pre-made scrapers for popular websites. Collect any web data at scale.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_brightdata?ms=1787295720000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `brightdata_crawl_api`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/brightdata`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/brightdata/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/brightdata/crawl/api` — Tool 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 BR
  - body: { items: object[], dataset_id: string, include_errors?: boolean, custom_output_fields?: string }
- `POST https://api.mcp.ai/api/brightdata/dataset/list` — Tool 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.
- `POST https://api.mcp.ai/api/brightdata/filter/dataset` — Tool to apply custom filter criteria to a marketplace dataset (BETA). Use after selecting a dataset to generate a filtered snapshot.
  - body: { files?: object[], filter: object, dataset_id: string, records_limit?: integer }
- `POST https://api.mcp.ai/api/brightdata/get/list/of/available/cities` — Tool to get available static network cities for a given country. Use when you need to configure static proxy endpoints after selecting a country.
  - body: { country: string, pool_ip_type?: string }
- `POST https://api.mcp.ai/api/brightdata/get/list/of/available/countries` — Tool 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.
- `POST https://api.mcp.ai/api/brightdata/get/snapshot/results` — Tool 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
  - body: { part?: integer, format?: string, compress?: boolean, batch_size?: integer, snapshot_id: string }
- `POST https://api.mcp.ai/api/brightdata/get/snapshot/status` — Tool to check the processing status of a crawl job using snapshot ID. Call before attempting to download results to ensure data collection is complete.
  - body: { snapshot_id: string }
- `POST https://api.mcp.ai/api/brightdata/list/web/unlocker/zones` — Tool to list your configured Web Unlocker zones and proxy endpoints. Use to view available zones for web scraping and bot protection bypass.
- `POST https://api.mcp.ai/api/brightdata/serp/search` — Tool 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 compet
  - body: { zone: string, format?: string, method?: string, country?: string, q_keywords: string, data_format?: string, search_engine?: string }
- `POST https://api.mcp.ai/api/brightdata/web/unlocker` — Tool 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 renderi
  - body: { url: string, zone: string, format?: string, country?: string, data_format?: string }

## Example prompts
- "What can I do in Bright Data?"
- "Show me a summary of my Bright Data account"

## More
- Page: https://mcp.ai/brightdata
- Agent spec (llms.txt): https://mcp.ai/brightdata/llms.txt
- Postman collection: https://mcp.ai/brightdata/postman.json