For the complete documentation index, see llms.txt. This page is also available as Markdown.

Google ADK Integration

Integrate Thordata MCP Server with Google ADK to give AI agents access to real-time SERP data and structured search results.

Connect the Google Agent Development Kit (ADK) to the ThorData MCP server (featuring over 60 tools) to enable web search and structured data extraction for Gemini-powered agents.

Remote MCP

1

Get your API token

  • Go to SERP API-API Token to create an API Token;

  • Copy your API Token (format as: sk_7qBRe***************************)

2

Install the required software 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

THORDATA_API_TOKEN = "YOUR_THORDATA_API_TOKEN"

root_agent = Agent(
model="gemini-2.5-pro",
name="THORdata_agent",
instruction="""Help users access web data using ThorData""",
tools=[
    McpToolset(
        connection_params=StreamableHTTPServerParams(
            url=f"https://mcp.thordata.com/THORDATA_API_TOKEN/mcp",
        ),
    )
],
)
4

Set environment variables (optional)

To enhance security, you can store the API token as an environment variable:

import os
THORDATA_API_TOKEN = os.getenv("THORDATA_API_TOKEN")

.envThen, create a file in the project directory:

THORDATA_API_TOKEN=your_ThorData_api_token_here
5

Testing to see if it works.

  • Please replace YOUR_THORDATA_API_TOKEN with your actual ThorData API token.

  • Run your Google ADK script.

  • You should see the agent perform a web search and provide a comprehensive response.

6

Monitor usage

View your API usage in the ThorData SERP API usage logs.

Last updated

Was this helpful?