Gemini

Connect Demandbase to Gemini Enterprise by creating a custom Google Agent Development Kit (ADK) agent, connecting the agent to the Demandbase MCP server, deploying it to Vertex AI Agent Engine, and registering it with Gemini Enterprise.

After the integration is configured, Google Workspace users can access Demandbase tools from Gemini.

Prerequisites for Connecting Demandbase to Gemini Enterprise

Before you connect Demandbase to Gemini Enterprise, make sure you have:

• A Google Cloud project with Vertex AI enabled.
• Permission to create and deploy Vertex AI Agent Engine resources.
• A supported Python version for ADK.
• Demandbase MCP server credentials.
• Google Workspace administrator access if you plan to register the agent in Gemini Enterprise.

Step 1: Set Up the Google ADK Environment

1. Log in to Google Cloud.
2. Install ADK and create a Python virtual environment. See:
   • ADK Python Github
   • ADK open source docs
   • ADK Quickstart (Vertex AI)
3. Verify that billing is enabled and your Google Cloud project is configured for Vertex AI.

Example:

gcloud auth login
gcloud config set project <YOUR_GCP_PROJECT_ID>
python3 -m venv .venv
source .venv/bin/activate
pip install google-adk

Step 2: Create the Google ADK Project

Create the ADK project and the files required to configure and deploy your agent.

Use the standard ADK project structure and include:

• A Python entry point for the agent.
• A dependency file, such as requirements.txt or pyproject.tom .
• A local configuration file for environment variables and secrets.

Important: Store Demandbase MCP connection details and credentials outside source control.

Step 3: Connect the ADK Agent to the Demandbase MCP Server

Configure the ADK McpToolset so the agent can access tools from the Demandbase MCP server. For information about configuring MCP tools in ADK, see Google's Model Context Protocol Tools​.

Use the following Demandbase MCP connection values:

The Demandbase MCP server exposes tools including:

• search_internal_account_database
• search_internal_person_database
• company_global_directory
• contact_global_directory
• get_demandbase_reference_data

Example:

from google.adk.agents import LlmAgent
from google.adk.tools import McpToolset

db_mcp = McpToolset(
    server_url="https://gateway.demandbase.com/mcp/servers/db-mcp",
    headers={
        "Authorization": f"Bearer {MCP_BEARER_TOKEN}",
    },
)

agent = LlmAgent(
    model="gemini-2.0-flash",
    name="demandbase_agent",
    tools=[db_mcp],
)

Step 4: Deploy the ADK Agent to Vertex AI Agent Engine

Deploy the configured ADK agent to Vertex AI Agent Engine so it can be registered with Gemini Enterprise. For deployment information, see Google's Scale your agents.

1. Package the agent and its dependencies.
2. Deploy the agent to Vertex AI Agent Engine.
3. Record the resulting reasoningEngine resource name.
4. Verify the deployment in the Google Cloud Console.

After deployment, confirm that the agent can connect to the Demandbase MCP server and retrieve the available tools.

Step 5: Register the ADK Agent in Gemini Enterprise

Register the deployed ADK agent with Gemini Enterprise to make it available to Google Workspace users. For registration information, see Google's Register and manage ADK agents hosted on Agent Runtime​.

1. Open the Google Cloud Console.
2. Go to Vertex AI > Agent Builder > Gemini Enterprise.
3. Open or create the Gemini Enterprise app you want to extend.
4. Select Agents.
5. Click + Add agent.
6. Select Custom agent via Agent Engine.
7. Enter the reasoningEngine resource name from Vertex AI Agent Engine.
8. Configure the authorization credentials required for the Google Workspace integration.

Demandbase Support provides the following authorization values:

1. clientId
2. clientSecret
3. tokenUri
4. authorizationUri

Step 6: Verify the Demandbase Connection

1. Open Gemini as a Google Workspace user.
2. Confirm that the custom agent is available.
3. Send a request that uses a Demandbase MCP tool.
4. Confirm that the agent returns Demandbase data.

A successful response confirms that Gemini Enterprise can access the deployed agent, authenticate the Google Workspace user, and retrieve Demandbase data through Demandbase MCP.

If the request fails, review the Vertex AI Agent Engine and agent runtime logs.

Troubleshoot the Demandbase Connection to Gemini Enterprise