# Bright Data
ID: 01-bright-data
Page: https://gtmmcps.com/tools/01-bright-data
JSON: https://gtmmcps.com/data/tools/01-bright-data.json
Documentation references: https://gtmmcps.com/docs/01-bright-data/
Category: Data & Enrichment
MCP support: official
Testing: RESEARCHED
API access: paid
Last checked: 2026-08-24
Endpoint check: repo-local; date: 2026-09-04

A general-purpose web-scraping/proxy infrastructure platform (residential proxies, browser automation, structured scraping APIs) that GTM engineers repurpose to pull LinkedIn, company-site, and directory data when off-the-shelf enrichment providers lack a record.

## MCP links
- https://github.com/brightdata/brightdata-mcp

## Sources
- https://github.com/brightdata/brightdata-mcp
- https://mcpservers.org/servers/brightdata/brightdata-mcp
- https://brightdata.com/pricing/mcp-server

## Research notes
Broader-scope than a purpose-built contact-enrichment vendor - it's web-data infrastructure, not a firmographic/contact database. Self-serve signup with pay-as-you-go and subscription plans; not enterprise-only for basic access. The MCP server alone exposes 69 tools spanning search, scraping, and browser automation.

## Named capabilities
Tool names below are reported by sources. Their presence is not a successful call.
- discover: Search the web and rank results by AI-driven relevance.; evidence: source; party: first-party
- extract: Scrape a webpage and extract structured data as JSON.; evidence: source; party: first-party
- list_dataset_fields: List the filterable fields of a searchable dataset; evidence: source; party: first-party
- scrape_as_html: Scrape a single webpage URL with advanced options for; evidence: source; party: first-party
- scrape_as_markdown: Scrape a single webpage URL with advanced options for; evidence: source; party: first-party
- scrape_batch: Scrape multiple webpages URLs with advanced options for; evidence: source; party: first-party
- scraping_browser_get_html: Get the HTML content of the current page. Avoid using this; evidence: source; party: first-party
- scraping_browser_get_text: Get the text content of the current page; evidence: source; party: first-party
- scraping_browser_go_back: Go back to the previous page; evidence: source; party: first-party
- scraping_browser_go_forward: Go forward to the next page; evidence: source; party: first-party
- scraping_browser_navigate: Navigate a scraping browser session to a new URL; evidence: source; party: first-party
- scraping_browser_screenshot: Take a screenshot of the current page; evidence: source; party: first-party
- scraping_browser_scroll: Scroll to the bottom of the current page; evidence: source; party: first-party
- search_dataset: Search a Bright Data dataset by a filter and get matching; evidence: source; party: first-party
- search_engine: Scrape search results from Google, Bing or Yandex. Returns; evidence: source; party: first-party
- search_engine_batch: Run multiple search queries simultaneously. Returns; evidence: source; party: first-party
- session_stats: Tell the user about the tool usage during this session; evidence: source; party: first-party

## CLI evidence
Status: none-found

Read current vendor documentation before configuring or running commands.