# Bright Data (MCP Server)

> Unblocked web search, scraping and structured data from 40+ platforms

- Type: MCP server
- Publisher: Bright Data (official)
- Categories: Data & Analytics, Research
- Website: https://github.com/brightdata/brightdata-mcp
- Source: https://github.com/brightdata/brightdata-mcp
- Transport: streamable-http
- Server URL: https://mcp.brightdata.com/mcp
- Launch command: npx @brightdata/mcp
- Sign-in: api-key
- Environment variables: API_TOKEN
- GitHub stars: 2662
- Listed: 2025-04-15

## About

Bright Data's MCP server gives agents search engine results, page scraping with bot-detection bypass, platform-specific structured extractors and remote browser automation. It offers a hosted endpoint with an API token or a local npx package, with a free monthly request tier.

## Install

1. **Connect it in ChatGPT** Turn on Developer mode in ChatGPT (Settings → Security and login), open Plugins, select + and paste https://mcp.brightdata.com/mcp as the MCP server URL. Add it to a chat from the composer's tools menu.

2. **Or add it to Codex or the API**

   Codex CLI:

   ```bash
   codex mcp add bright-data --url https://mcp.brightdata.com/mcp --bearer-token-env-var API_TOKEN
   ```

   config.toml:

   ```toml
   [mcp_servers.bright-data]
   url = "https://mcp.brightdata.com/mcp"
   bearer_token_env_var = "API_TOKEN"
   ```

   Responses API:

   ```python
   import os
   from openai import OpenAI
   
   client = OpenAI()
   
   response = client.responses.create(
       model="gpt-6-astra",
       tools=[{
           "type": "mcp",
           "server_label": "bright_data",
           "server_url": "https://mcp.brightdata.com/mcp",
           "authorization": os.environ["API_TOKEN"],
           "require_approval": "never",
       }],
       input="Search Google for 'best CRM for startups' and return the top results",
   )
   print(response.output_text)
   ```

## Tools

- `search_engine`
- `search_engine_batch`
- `scrape_as_markdown`
- `scrape_as_html`
- `scrape_batch`
- `web_data_amazon_product`
- `web_data_amazon_product_reviews`
- `scraping_browser_navigate`
- `scraping_browser_snapshot`
- `scraping_browser_screenshot`
- `session_stats`

## Example prompts

- "Search Google for 'best CRM for startups' and return the top results"
- "Scrape this Amazon product page as markdown"
- "Get reviews for this Amazon product"
- "Open a browser, go to this page and take a screenshot"

## Related

- [Supabase](https://chatgptplugins.directory/mcp/supabase.md): Manage Supabase databases, migrations, edge functions and logs
- [Fetch](https://chatgptplugins.directory/mcp/fetch.md): Fetch web pages and convert them to markdown for LLMs
- [Graphiti MCP](https://chatgptplugins.directory/mcp/graphiti.md): Temporal knowledge graph memory for agents, by Zep
- [MCP Toolbox for Databases](https://chatgptplugins.directory/mcp/mcp-toolbox-databases.md): Google's open-source MCP server for 20+ databases
- [DeepWiki](https://chatgptplugins.directory/mcp/deepwiki.md): Ask questions about any public GitHub repo using DeepWiki's generated docs
- [PostHog](https://chatgptplugins.directory/mcp/posthog.md): Query product analytics, feature flags, experiments and errors in PostHog

---
Source: https://chatgptplugins.directory/mcp/bright-data · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.