How to Use the DealHub CPQ MCP in Google ADK

Q: How do I connect Google ADK to the DealHub CPQ MCP server?

You use the McpToolset class from the Google ADK library, pointing it to the Vinkius server URL. Pass this toolset to your LlmAgent constructor, and it will expose the DealHub CPQ tools to your Gemini model.

Q: What if I only want my agent to read from DealHub CPQ and not write data?

The McpToolset in Google ADK has a toolnames filter. You can use it to expose only the read-only tools like getopportunity, getquotestatus, and listopportunities, preventing the agent from calling write operations.

Q: Can I run a Google ADK agent with DealHub CPQ tools from my terminal?

You can. The Google ADK LlmAgent supports both Stdio and HTTP transports. It's straightforward to build a command-line tool that interacts with your agent to manage DealHub CPQ for quick tasks or testing.

Let your Gemini agent manage DealHub CPQ. Connect Google ADK to your sales data and automate quotes, opportunities, and CRM syncs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DealHub CPQ MCP to Google ADK

Create your Vinkius account to connect DealHub CPQ to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup DealHub CPQ with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Act on Your Google Cloud Data

Your data probably lives in BigQuery. With Google ADK, your Gemini agent can analyze that data and then take direct action in DealHub. For instance, after identifying a high-value prospect, the agent can immediately use `create_opportunity` to open a new deal. This closes the loop between analytics and operations. The agent can then follow up by generating a quote with `create_quote`, linking the new CPQ sequence directly to the CRM record. It’s all driven by the data you already have in Google Cloud.

Complex Opportunity Management with Gemini

Gemini's large context window is a major advantage here. You can feed an agent an entire deal history—emails, notes, past quotes—and have it decide the next best action. It can use `get_opportunity` to check the current state, then `update_opportunity` to make precise changes based on its analysis. This MCP Server exposes the tools, and Google ADK provides the reasoning power. Your agent can run complex logic, like comparing a new request against existing deal terms before updating a record, which reduces manual review time for your sales team.

Automate Reporting with a Google ADK MCP Server

Build agents that handle reporting for the whole team. An agent can run `list_opportunities` and `list_quotes` on a schedule, then push the formatted results directly into a Google Sheet or BigQuery table for analysis. For system-level tasks, you can use tools like `list_users` for audits or `sync_crm` for data cleanup. Because you're in the Google Cloud ecosystem, you can trigger these agent actions with Cloud Functions or schedule them with Cloud Scheduler, building a fully automated system.

Setup guide

Set up DealHub CPQ MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with DealHub CPQ tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="DealHub CPQ_agent",
    model="gemini-2.0-flash",
    instruction="You have access to DealHub CPQ tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by DealHub. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect DealHub CPQ now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about DealHub CPQ MCP in Google ADK

You use the `McpToolset` class from the Google ADK library, pointing it to the Vinkius server URL. Pass this toolset to your `LlmAgent` constructor, and it will expose the DealHub CPQ tools to your Gemini model.

Yes, that's the main idea. Google ADK is designed to work within the GCP ecosystem. Your agent can query BigQuery for insights and then use the DealHub CPQ tools like `create_opportunity` to act on those insights in the same workflow.

The `McpToolset` in Google ADK has a `tool_names` filter. You can use it to expose only the read-only tools like `get_opportunity`, `get_quote_status`, and `list_opportunities`, preventing the agent from calling write operations.

You can. The Google ADK `LlmAgent` supports both Stdio and HTTP transports. It's straightforward to build a command-line tool that interacts with your agent to manage DealHub CPQ for quick tasks or testing.

Your connection is secured through the Vinkius-managed MCP server. The server uses an ephemeral, single-use sandbox for every request, and your auth token is the only key. Google ADK communicates with this hardened endpoint, ensuring your opportunity, quote, and user data is processed in isolation.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript