Bright Data Skills plugin
The official Bright Data plugin: 21 skills for Google search, page scraping, ready scrapers, proxies and the Bright Data MCP server
- 268 ★ on the repository
- Last commit
- MIT
Broad access
Why this level
- The Bright Data key starts paid requests, and in the MCP URL it sits in plain text in the configuration
- Scraping social networks and profiles collects personal data, and the skills bypass bot protection and CAPTCHAs
- bdata login saves the key to disk and creates the cli_unlocker and cli_browser zones in your account
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/bright-data-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- The Bright Data key starts paid requests, and in the MCP URL it sits in plain text in the configuration
- Scraping social networks and profiles collects personal data, and the skills bypass bot protection and CAPTCHAs
- bdata login saves the key to disk and creates the cli_unlocker and cli_browser zones in your account
This is third-party code. Review the repository files before installing.
What it does
Bright Data Skills is a Bright Data plugin for Claude Code that adds 21 web data skills. The search and scrape skills return Google results as JSON and pages as clean markdown, bypassing bot protection, CAPTCHAs and JavaScript rendering. The data-feeds skill runs ready scrapers through the bdata CLI (pipelines search, info, run commands) for Amazon, LinkedIn, Instagram, TikTok, YouTube and other platforms. The bright-data-mcp skill teaches the agent to choose among the thirty-plus tools of the Bright Data MCP server and use them instead of the built-in WebFetch and WebSearch. The other skills produce code and reports: scraper-builder writes scrapers for a site, brightdata-proxy gives working code for datacenter, ISP, residential and mobile proxies, competitive-intel and live-research prepare competitor analyses and cited research, and the Python and JavaScript SDK skills help write code on brightdata-sdk and @brightdata/sdk. The entry point is agent-onboarding: it installs the CLI, walks through OAuth sign-in and routes to the right skill.
Who it is for. For developers, analysts and marketers who want an agent to collect data from websites past blocks and to write scrapers on Bright Data infrastructure.
Good fit when
- You need page text as clean markdown from a site that blocks ordinary requests
- You need structured data from Amazon, LinkedIn, Instagram, TikTok or YouTube through a ready scraper
- You want a price and competitor comparison built on live site data
- You need a scraper for a specific site, from page analysis to pagination
- You need code that routes requests through residential or mobile proxies with the right targeting
Not a fit when
- You only need a one-off collection from an open site without protection: the built-in WebFetch and WebSearch are enough
- You have no Bright Data account: the infrastructure needs a key and a zone
- You need proxy setup in the Bright Data control panel: the brightdata-proxy skill explains usage and does not walk through the panel
- You cannot send URLs and queries to a third-party service: all requests go through Bright Data
Example request
Use Bright Data to get structured data for the product at this Amazon link and compare the price with three competitorsLimitations
A Bright Data account and API key are required. For a quick start you create a Web Unlocker zone and set the BRIGHTDATA_API_KEY and BRIGHTDATA_UNLOCKER_ZONE variables, or sign in with bdata login, which saves the key and creates the cli_unlocker and cli_browser zones by itself. Residential and mobile networks have an access policy, and the skill mentions identity verification (KYC).
The CLI has a budget check, so keep an eye on the account spend. Connecting MCP through a URL with a token keeps the key in plain text in the configuration.
How to disable. Remove the plugin from the /plugin menu in Claude Code and, if you connected MCP by URL, delete the brightdata entry from the config. Revoke the key in the Bright Data dashboard: if you signed in with bdata login, it is saved locally on your machine.
FAQ
How do I start with Bright Data in Claude Code?
The agent-onboarding skill describes the shortest path: install the CLI with npm install -g @brightdata/cli, sign in with bdata login and get routed to the right skill. Without the CLI you can take a key from the Bright Data dashboard, create a Web Unlocker zone and set BRIGHTDATA_API_KEY and BRIGHTDATA_UNLOCKER_ZONE.
How do I connect the Bright Data MCP server?
Add a brightdata server to your MCP configuration with the URL https://mcp.brightdata.com/mcp?token=YOUR_TOKEN. All tools are enabled by default, and the groups parameter (scrapers, browser, advanced_scraping, geo) or tools narrows the set.
How is Bright Data Skills different from Firecrawl MCP?
Firecrawl MCP is a separate server for search and scraping. Bright Data Skills is a set of 21 skills around Bright Data infrastructure: Web Unlocker, SERP API, ready scrapers, proxies, the MCP server and SDKs, and the skills choose the path by task.
What does the data-feeds skill do?
It finds a ready scraper with bdata pipelines search, shows its parameters with info and runs it with run. The README names thousands of ready scrapers, including Amazon, LinkedIn, Instagram, TikTok and YouTube.
Which proxies does the brightdata-proxy skill support?
It generates working code for datacenter, ISP, residential and mobile networks: network and IP pool choice, targeting through the username, the SSL certificate, and integrations for cURL, Python (requests, httpx, aiohttp, Scrapy), Node (fetch, axios), Playwright, Puppeteer and Selenium.
Discussion
No questions or reviews yet.
Related
PluginsHyperbrowser MCP
Hyperbrowser MCP Server
The official MCP server for Hyperbrowser cloud browsers: page scraping and crawling, structured data, Bing search and three browser agents
A web research skill: SearXNG searches, Camofox reads pages and CloakBrowser opens sites that check their visitors
Browserbase's official skill set that gives Claude Code web access: browser automation, search, page fetching and UI testing
Web Access
web-access
A web access skill that picks between search, page fetch and driving your own browser over CDP
A web search skill with no MCP server: four command-line clients search the web and 16 vertical domains, in batches and with page extraction
A CLI and MCP server that lets an agent drive your real Chrome with its logged-in sessions: 103 commands across 36 platforms plus browser automation
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Bright Data Skills (this entry) | yes | 268 | ||
| Firecrawl MCP Server | yes | API key | 7,712 | a separate Firecrawl MCP server for search and scraping, while this has skills around Bright Data infrastructure |
| Apify Agent Skills | no | 2,473 | skills for the Apify Actor platform, while this has Bright Data Web Unlocker, SERP API, scrapers and proxies | |
| google-surf-mcp | no | not required | 291 | an MCP server that searches Google and Scholar |
README in short
The description opens with an overview of what the plugin does and a table of 21 skills. Detailed sections follow: agent onboarding, a quick start with getting the key and a zone, the MCP skill with the server URL, competitive intelligence, the scraper builder, proxies and guides for the Python and JavaScript SDKs. The CLI section at the end collects the bdata commands, including skill installation.