An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Bright Data to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn your AI agent into a professional data engineer.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Bright Data.

  1. 01

    Get dataset snapshot

    Downloads completed scraping results as structured JSON records. It identifies dead pages or bad input patterns during the process.

  2. 02

    List datasets

    Browses the library of over 100 available datasets. Use this to find specific dataset IDs for your tasks.

  3. 03

    Get zone info

    Checks the configuration of a specific proxy zone. It returns details on type, status, and bandwidth settings.

  4. 04

    Get all zones

    Lists every proxy zone configured in your Bright Data account. You should run this before attempting to send requests to ensure your zone names are correct.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Bright Data.

  1. 05

    Get dataset progress

    Monitors the status of an active data collection. It reports if a job is running or ready, along with record and error counts.

  2. 06

    Get zone passwords

    Retrieves proxy credentials for use in external automation frameworks like Selenium or Playwright. Handle these credentials with care.

  3. 07

    Get account status

    Verifies your API key and account standing. Run this if you encounter authentication errors with other capabilities.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Bright Data.

  1. 08

    List browser sessions

    Shows the most recent Scraping Browser sessions. You can filter these by status, duration, or bandwidth usage.

  2. 09

    Send request

    Executes a single web request to scrape a URL or pull SERP data. It uses Web Unlocker to bypass bot detection or SERP API zones for search engine results.

  3. 10

    Trigger dataset

    Starts an asynchronous scraping job for sources like LinkedIn, Amazon, or Instagram. You provide a URL or keyword to begin the collection.

Real work

What teams actually run

01

Competitor Intelligence

An agent monitors search engine results to track how competitor rankings change over time.

02

E-commerce Monitoring

You trigger a dataset job to collect product pricing and reviews from Amazon.

03

Social Media Analysis

The agent scrapes LinkedIn posts to extract engagement metrics like reactions and comments.

04

Automated Testing

Developers use the agent to check proxy zone status and manage browser sessions during testing.

Automate a task

Put Bright Data to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Bright Data works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Bright Data to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1026ms average. Fast in production.

Bright Data is checked daily against the live service.

Daily averagePeak 1179ms
Oct 3Today
Fastest day
744ms
Slowest day
1179ms
14-day trend
Stable+3%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Bright Data, so you can see the experience inside your AI.

It does not authenticate your account with Bright Data. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Bright Data Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_Z06xKXBLbhmRgabDfSd6BBkkFtoyph9gsiWpikY1/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Bright Data capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "bright-data-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_Z06xKXBLbhmRgabDfSd6BBkkFtoyph9gsiWpikY1/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Bright Data in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Bright Data owners hand off.

This MCP is built for professionals who need to turn web data into actionable intelligence without writing custom scraping infrastructure.

  • 01

    Data Scientists

    They hand off the task of gathering large training datasets to their agent.

  • 02

    Developers

    They use the agent to debug browser sessions and manage proxy zones from their editor.

  • 03

    Market Researchers

    They instruct the agent to track competitor movements and search engine rankings.

FAQ

Questions Bright Data owners ask.

  • 01

    How do I bypass website blocks?

    You can use the send_request capability with a Web Unlocker zone to bypass anti-bot protections on protected sites.

  • 02

    Can I use these proxies in my own Python scripts?

    Yes. Use the get_zone_passwords capability to retrieve credentials for direct connections in frameworks like Selenium or Playwright.

  • 03

    How long does it take to collect a large dataset?

    It depends on the source. For example, LinkedIn scraping typically takes between 60 and 120 seconds per URL.

  • 04

    How do I know when my data collection is finished?

    You can use the get_dataset_progress capability to check if the status is 'ready' before attempting to download the results.

  • 05

    What happens if I don't have any proxy zones set up?

    You can use get_all_zones to check your account. If the list is empty, you will need to create zones at the Bright Data control panel.

  • 06

    What is the workflow for scraping a LinkedIn post?

    Use trigger_dataset with the LinkedIn Posts dataset ID (gd_lyy3tktm25m4avu764) and a direct post URL (e.g., https://www.linkedin.com/feed/update/urn:li:activity:...). This returns a snapshot_id. Then poll get_dataset_progress every 15–30 seconds until the status is ready. LinkedIn scraping typically takes 60–120 seconds. Finally, call get_dataset_snapshot to retrieve the structured data including post content, author details, reactions, and comment count.

  • 07

    Why does send_request fail with a zone error?

    The send_request capability requires an active proxy zone (Web Unlocker or SERP API). If your account has no zones configured, the request will fail. Run get_all_zones first to check your available zones. If the list is empty, you need to create a zone in the Bright Data dashboard before using send_request.

  • 08

    Which URL formats does the LinkedIn Posts dataset accept?

    The LinkedIn Posts dataset (gd_lyy3tktm25m4avu764) only accepts direct post URLs matching the pattern linkedin.com/(pulse|posts|feed/update). Valid examples: https://www.linkedin.com/feed/update/urn:li:activity:1234567890 or https://www.linkedin.com/posts/username_title-activity-1234567890. Search result pages, profile pages, and hashtag pages are not supported.

  • 09

    How do I find the right dataset ID for my use case?

    Use the list_datasets capability to browse all 100+ available datasets. Common IDs: LinkedIn Posts (gd_lyy3tktm25m4avu764), LinkedIn People (gd_l1viktl72bvl7bjuj0), LinkedIn Companies (gd_l1vikfnt1wgvvqz95w), Amazon Products (gd_l7q7dkf244hwjntr0), Instagram Profiles (gd_l1vikfch901nx3by4), Google Maps (gd_m8ebnr0q2qlklc02fz).

Explore

More in Developer Tools

Suggestions

Connect Bright Data to Claude, Cursor, ChatGPT & more