The Web MCP enables AI assistants to access real-time web data without being blocked or rate-limited. It provides seamless integration for various AI models to enhance their capabilities with live information.
From the registry: Bright Data's Web MCP server enabling AI agents to search, extract & navigate the web
Please install the `brightdata-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Bright Data API token** — Sign up at brightdata.com and get API token (https://brightdata.com/ai/mcp-server)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["@brightdata/mcp"]
- required environment variables:
- `API_TOKEN`: Bright Data API token (example: `<placeholder>`)
- optional environment variables:
- `PRO_MODE`: Enable all 60+ pro tools (example: `true`)
- `RATE_LIMIT`: Custom rate limit (example: `100/1h`)
- `WEB_UNLOCKER_ZONE`: Custom Web Unlocker zone (example: `mcp_unlocker`)
- `BROWSER_ZONE`: Custom Browser zone (example: `mcp_browser`)
- `POLLING_TIMEOUT`: Timeout for web_data_* polling (seconds) (example: `600`)
- `BASE_TIMEOUT`: Request timeout for base tools (example: `60`)
- `BASE_MAX_RETRIES`: Max retries on transient errors (0-3) (example: `1`)
- `GROUPS`: Comma-separated tool group IDs (example: `ecommerce,browser`)
- `TOOLS`: Comma-separated individual tool names (example: `extract,scrape_as_html`)
Note: Hosted HTTP also available at https://mcp.brightdata.com/mcp?token=<token>.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.API_TOKENrequiredToken for authenticating API requests.AI-powered browser automation — navigate, click, fill forms, and extract data from any website.