Our take
Activeregular commits and releases- Activity
- 66
- Community
- 53
- Issues
- 21
- Pull requests
- 65
+50 stars in the last 30 days
This is a broad, actively maintained MCP option for teams that need live web data and are comfortable routing requests through Bright Data’s service.
Good fit if
- Your AI agent needs search, scraping, structured data, or remote browser capabilities through MCP.
- You want Bright Data to handle access obstacles such as bot detection and CAPTCHA challenges.
- Your team can use a Bright Data API token and work within its free tier or paid usage model.
Look elsewhere if
- You need a web-data solution that does not depend on Bright Data’s hosted services, account, or usage limits.
- You only need a narrow search or page-fetch tool and do not need the server’s wider set of capabilities.
- Your deployment cannot run Node.js or connect to Bright Data’s services.
All health signals
| Last commit | 2026-10-18 (1 day ago) |
|---|---|
| Commits, last 90 days | 52 |
| Releases, last 12 months | 18 (latest v4.0.0, 2026-10-18) |
| Contributors | 19 (top contributor: 59% of commits) |
| Issues closed, last 90 days | 0 |
| Pull requests merged, last 90 days | 12 (typically merged in 0 days) |
| Project age | 18 months |
Checked on 2026-10-20 with the GitHub API.
Project history
Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.
Stars
2,730Forks
336Change since Nov 17, 2026: +2 stars·0 forks
Overview
Bright Data MCP is a Model Context Protocol (MCP) server built on Bright Data’s web data and unblocking services. It gives AI agents, coding agents, chat assistants, and other MCP-compatible clients access to public web search, page content, structured data, and browser automation, including on sites that block ordinary web requests.
It can connect through Bright Data’s hosted server or run locally with Node.js. The central trade-off is convenience and breadth: Bright Data handles the infrastructure for access to public pages and platform-specific data, while usage depends on a Bright Data account and its request limits or pricing.
Key Features
- Search Google, Bing, and Yandex, with batch search for multiple queries.
- Scrape pages as Markdown or HTML, with automatic handling of bot protection, CAPTCHAs, and proxy rotation.
- Find and run Bright Data’s pre-built scrapers to retrieve structured data from platforms and sites.
- Automate a remote browser session to navigate pages, interact with controls, and capture page content or screenshots.
- Extract structured JSON from pages using AI, including with a custom extraction prompt.
- Collect responses from ChatGPT and Perplexity as structured results.
- Limit enabled tools by group or individual tool name to reduce the tool set exposed to an agent.
Use Cases
- Research assistants can search for current information and retrieve source pages instead of relying only on model training data.
- E-commerce and market research teams can collect product details, prices, reviews, and competitor information from supported platforms.
- Coding agents can look up current npm and PyPI package information or retrieve GitHub repository data through scrapers.
- Agents that need to work with dynamic or interactive pages can use remote browser automation rather than relying on a basic HTTP fetch.
- Brand and marketing teams can compare how ChatGPT and Perplexity answer prompts about a company or product.
What you need
Detected in the repository
- Node.js (from package.json)
- A Dockerfile, so it can run in a container
- A test suite and automated checks on GitHub Actions
License in plain words
MITpermissive
- Commercial use: yes
- Modify and redistribute: yes
- You must keep: the copyright and license notice
- Share your changes: no
A summary, not legal advice: the LICENSE file is what applies.
Getting Started
For a local MCP server, configure your client to run:
npx @brightdata/mcp
Set API_TOKEN to a token from your Bright Data account. Alternatively, connect an MCP client to https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN. See the README for client-specific setup and tool configuration.
Alternatives
- stagehand: Stagehand is a browser automation SDK with structured extraction, while brightdata-mcp also offers web search and Bright Data’s scraping and unblocking services.
- browserable: Browserable provides self-hosted natural-language browser automation, while brightdata-mcp combines browser control with web search, scraping, and structured extraction.
| Project | Language | License | Stars | Status |
|---|---|---|---|---|
| brightdata-mcp | JavaScript | MIT | 2.7k | Active |
| stagehand | TypeScript | MIT | 25.5k | Active |
| browserable | JavaScript | MIT | 1.2k | Inactive |
Considerations
- The server requires a Bright Data API token. Its README describes a monthly free request allowance and pay-as-you-go pricing, so teams should check current terms and set a suitable spending cap before production use.
- Access to web content is not the same as permission to reuse it. Teams remain responsible for checking applicable site terms, privacy requirements, and data-handling rules.
- The project is actively maintained, with recent commits and releases and contributions from multiple developers. The measured period also shows no closed issues, so issue-resolution responsiveness is harder to assess from that signal alone.
- Local use requires Node.js. A hosted option avoids local installation but still requires network access to Bright Data.
- The repository is MIT-licensed; review the license terms when incorporating or redistributing the software.
Found this useful?
Share it with someone who would like brightdata-mcp.