Overview
Bright Data MCP is the easiest way to empower your AI agents and applications with reliable, real-time access to the open web - all while handling the complexity of scraping, unblocking, and data structuring for you.
Getting Started: Before using MCP, please ensure the following prerequisites are met: 1.Node.js is installed and up to date. 2.You have an active Bright Data account (a registration link will be provided after subscription). 3.You generated an API key with Admin permissions from your Bright Data user settings. 4.To enable browser automation features, ensure you have a Browser API zone set up. If not, you can create one in your Bright Data control panel or specify an existing one using the BROWSER_ZONE environment variable.
Highlights
- Real Time Web Access
- Bot Detection Evasion
- Structured Data Extraction
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Free trial
Dimension | Description | Cost/month |
|---|---|---|
500 | STARTER | $500.00 |
Dimensions summary
Top-of-mind questions for buyers
Vendor refund policy
Cancel at any time. Unless otherwise specified, funds for committed periods or usage will not be refundable.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
API-Based Agents & Tools
API-Based Agents and Tools integrate through standard web protocols. Your applications can make API calls to access agent capabilities and receive responses.
Additional details
Usage instructions
- Make sure you have an account on brightdata.com
- Get your API key from the user settings page, or from the welcome email you received
Optional: 3. Configure rate limiting:
- Set the RATE_LIMIT environment variable to control API usage
- Format: limit/time+unit (e.g., 100/1h for 100 calls per hour)
- Supported time units: seconds (s), minutes (m), hours (h)
- Examples: RATE_LIMIT=100/1h, RATE_LIMIT=50/30m, RATE_LIMIT=10/5s Rate limiting is session-based (resets when server restarts)
- Create a custom Web Unlocker zone
- By default, we create a Web Unlocker zone automatically using your API token
- For more control, you can create your own Web Unlocker zone in your control panel and specify it with the WEB_UNLOCKER_ZONE environment variable
- Create a custom Browser API zone:
- By default, we create a Browser API zone automatically using your API token.
- For more control, you can create your own Browser API zone in your control panel and specify it with the BROWSER_ZONE environment variable Other MCP Clients: To use this MCP server with other agent types, you should adapt the following to your specific software: -Before running the server, make sure the API_TOKEN=<your-token> environment variable is set -The full command to run the MCP server is npx @brightdata/mcp --> macOS / Linux (bash/zsh) export API_TOKEN=your-token npx @brightdata/mcp --> Windows (Command Prompt) set API_TOKEN=your-token npx @brightdata/mcp --> Windows (PowerShell) $env:API_TOKEN="your-token" npx @brightdata/mcp
Resources
Support
Vendor support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Customer reviews
All-in-One Tooling with Outstanding Pro-Bono Support from BrighData
Reliable Scraper with User-Friendly Self-Service UI
Consistently Fresh LinkedIn Data with an Easy-to-Integrate API
The API is also straightforward to integrate into our scripts: we trigger a collection, monitor its progress, and then download the results. We run it daily through automated jobs, and we receive an email when each snapshot is ready.
Support has been fair and reasonable. Once, our script accidentally created large snapshots that we never downloaded. We explained what happened, and they issued a refund. That experience is a big reason we trust them with a pay-as-you-go account.
The default API token is limited. Our token could create snapshots, but it could not cancel them or read the account balance. So our automation could not stop itself or check what it spent.
Some things break automated jobs without warning. API tokens expire, scraper output schemas change, and the account is suspended when the balance runs out. Each one stops our daily jobs until someone fixes it by hand.
The API has two sets of similar routes (v3 and older ones), and it is easy to call the wrong one. Every snapshot also sends its own email, which fills the inbox fast.
It solves three problems for us.
First, finding the right companies. Every day we scan new US job posts. When a company hires someone to train its sales, partner, or customer teams, that tells us it is about to grow or launch something. We built our ideal customer profile from 344 of these job posts, so it's based on real hiring data, not guesses.
Second, knowing the right person. We check LinkedIn profiles to confirm a contact's current title and company before we reach out.
Third, keeping our CRM true. Every week we re-check whether our contacts still work at the same company. When someone leaves, we update the record and stop writing to the wrong address.
The benefit: our outreach reaches the right person at the right time, and we spend no engineering time on proxies or scrapers. That matters a lot for a team our size.