Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.brightdata.com/llms.txt

Use this file to discover all available pages before exploring further.

Building an AI startup?

You might be eligible for our Startup Program. Get fully funded access to the infrastructure you’re reading about right now (up to $20K value).

​
Remote MCP

1

Get your API token

  1. Go to Bright Data user settings
  2. Copy your API token (it looks like: 2dceb1aa0***************************)
2

Install required packages

pip install google-adk
3

Configure your MCP server

from google.adk.agents import Agent
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPServerParams
from google.adk.tools.mcp_tool.mcp_toolset import MCPToolset

BRIGHTDATA_API_TOKEN = "YOUR_BRIGHTDATA_API_TOKEN"

root_agent = Agent(
model="gemini-2.5-pro",
name="brightdata_agent",
instruction="""Help users access web data using Bright Data""",
tools=[
    MCPToolset(
        connection_params=StreamableHTTPServerParams(
            url=f"https://mcp.brightdata.com/mcp?token={BRIGHTDATA_API_TOKEN}",
        ),
    )
],
)
4

Set up environment variables (optional)

For better security, you can store your API token as an environment variable:
import os
BRIGHTDATA_API_TOKEN = os.getenv("BRIGHTDATA_API_TOKEN")
Then create a .env file in your project directory:
BRIGHTDATA_API_TOKEN=your_brightdata_api_token_here
5

Test it works

  1. Replace YOUR_BRIGHTDATA_API_TOKEN with your actual Bright Data API token
  2. Run your Google ADK script
  3. You should see the agent execute web searches and provide comprehensive responses
6

Monitor usage

  1. View your API usage at My Zones in your Bright Data dashboard
  2. Your free tier includes 5,000 requests per month

​
Local MCP Server

1

Get your API token

  1. Go to Bright Data user settings
  2. Copy your API token (it looks like: 2dceb1aa0***************************)
2

Install required packages

pip install google-genai
npm install -g @brightdata/mcp
3

Configure your local MCP server

from google.adk.agents import Agent
from google.adk.tools.mcp_tool.mcp_session_manager import StdioConnectionParams
from google.adk.tools.mcp_tool.mcp_toolset import MCPToolset
from mcp import StdioServerParameters

BRIGHTDATA_API_TOKEN = "YOUR_BRIGHTDATA_API_TOKEN"

root_agent = Agent(
model="gemini-2.5-pro",
name="brightdata_agent",
instruction="Help users access web data using Bright Data",
tools=[
    MCPToolset(
        connection_params=StdioConnectionParams(
            server_params = StdioServerParameters(
                command="npx",
                args=[
                    "@brightdata/mcp",
                ],
                env={
                    "API_TOKEN": BRIGHTDATA_API_TOKEN,
                    "PRO_MODE": "true",  # Optional: Enable all 60+ tools
                }
            ),
            timeout=300,
        ),
    )
],
)
4

Test it works

  1. Replace YOUR_BRIGHTDATA_API_TOKEN with your actual Bright Data API token
  2. Run your Google ADK script with the local MCP server
  3. The agent will use the locally installed MCP server to access all available tools
5

Monitor usage

  1. View your API usage at My Zones in your Bright Data dashboard
  2. Your free tier includes 5,000 requests per month

​
Available Tools

The Bright Data MCP server provides access to powerful web scraping capabilities:
  • Rapid Mode (Free Tier): 4 essential tools including search, scraping, and extraction
  • Pro Mode: 60+ additional tools including batch operations, browser automation, and structured data APIs for major platforms
View complete tool documentation Visit Google ADK docs