An MCP interface into the Bright Data toolset
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
API_TOKENAPI keyrequiredYour API key for Bright Data
Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
scraping_browser_navigateNavigate a scraping browser session to a new URLNavigate a scraping browser session to a new URL
No input schema was published for this tool.
scraping_browser_go_backGo back to the previous pageGo back to the previous page
No input schema was published for this tool.
scraping_browser_go_forwardGo forward to the next pageGo forward to the next page
No input schema was published for this tool.
scraping_browser_snapshotNo description publishedThis tool published no description. Forge does not invent one.
scraping_browser_click_refNo description publishedThis tool published no description. Forge does not invent one.
scraping_browser_type_refNo description publishedThis tool published no description. Forge does not invent one.
scraping_browser_screenshotTake a screenshot of the current pageTake a screenshot of the current page
No input schema was published for this tool.
scraping_browser_get_htmlGet the HTML content of the current page. Avoid using thisGet the HTML content of the current page. Avoid using this
No input schema was published for this tool.
scraping_browser_get_textGet the text content of the current pageGet the text content of the current page
No input schema was published for this tool.
scraping_browser_scrollScroll to the bottom of the current pageScroll to the bottom of the current page
No input schema was published for this tool.
scraping_browser_scroll_to_refNo description publishedThis tool published no description. Forge does not invent one.
scraping_browser_network_requestsNo description publishedThis tool published no description. Forge does not invent one.
scraping_browser_wait_for_refNo description publishedThis tool published no description. Forge does not invent one.
scraping_browser_fill_formNo description publishedThis tool published no description. Forge does not invent one.
web_scraping_strategyDecision tree for picking the right Bright Data tool.Decision tree for picking the right Bright Data tool.
No input schema was published for this tool.
diagnose_scraping_approachRun a two-step diagnostic to discover the correctRun a two-step diagnostic to discover the correct
No input schema was published for this tool.
search_engineNo description publishedThis tool published no description. Forge does not invent one.
scrape_as_markdownNo description publishedThis tool published no description. Forge does not invent one.
search_engine_batchNo description publishedThis tool published no description. Forge does not invent one.
scrape_batchNo description publishedThis tool published no description. Forge does not invent one.
scrape_as_htmlNo description publishedThis tool published no description. Forge does not invent one.
extractNo description publishedThis tool published no description. Forge does not invent one.
discoverNo description publishedThis tool published no description. Forge does not invent one.
list_dataset_fieldsNo description publishedThis tool published no description. Forge does not invent one.
search_datasetNo description publishedThis tool published no description. Forge does not invent one.
session_statsNo description publishedThis tool published no description. Forge does not invent one.
9 of 26 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
An MCP interface into the Bright Data toolset
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
119 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+107 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.