How to Use the HubSpot MCP in Google ADK

Q: How do I configure the HubSpot integration in Google ADK?

Initialize McpToolset using StreamableHttpServerParameters with your Vinkius URL. Pass this toolset directly to the tools array when building your LlmAgent.

Q: Can Google ADK filter which HubSpot tools the agent sees?

You pass a toolnames list to the toolset constructor to restrict access. This lets you expose listdeals while hiding destructive tools like removecontact.

Q: How does the HubSpot MCP Server handle long context windows?

Gemini ingests massive payloads returned by listcontacts and listcompanies. The agent holds the entire CRM export in its context window for deep reasoning against your Vertex AI models.

Q: Can I join HubSpot data with BigQuery using Google ADK?

Your agent pulls deal IDs using getdealdetails and immediately writes that data into your enterprise data warehouse. The ADK handles the orchestration between the MCP tools and your Google Cloud infrastructure.

Connect HubSpot to Google ADK and let Gemini agents analyze millions of CRM records alongside BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HubSpot MCP to Google ADK

Create your Vinkius account to connect HubSpot 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 HubSpot with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Gemini massive HubSpot datasets

The HubSpot MCP server dumps your sales database straight to your Google ADK agents via `list_companies` and `list_contacts`. Gemini packs a massive context window. It ingests thousands of records at once without dropping a single detail. You pull raw CRM data and cross-reference it with your existing BigQuery tables in a single prompt. The agent calls `get_company_info` to fill in missing firmographics before running its analysis on Vertex AI.

Map complex sales associations

Your agent traverses the CRM graph by calling `link_crm_objects` to connect isolated records. When a marketing campaign generates a massive list of leads, the Google ADK agent processes them in bulk and associates them with the right accounts. If the agent needs to verify an owner, it runs `list_hubspot_users` and assigns the newly linked records to the correct sales rep. You filter the exposed tools using the `tool_names` parameter to keep the agent focused strictly on association tasks.

Search and clean CRM records with MCP

This MCP integration gives your Google Cloud agents the ability to find and purge bad data using `search_contacts` and `remove_contact`. Enterprise databases always drift into chaos. An autonomous agent runs nightly sweeps to find duplicates. Before deleting anything, the agent verifies the record structure using `get_object_schema`. It pulls the specific fields with `get_contact_details` to ensure it only removes actual spam submissions.

Setup guide

Set up HubSpot 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 HubSpot 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="HubSpot_agent",
    model="gemini-2.0-flash",
    instruction="You have access to HubSpot 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 HubSpot. 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 HubSpot 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 HubSpot MCP in Google ADK

Initialize `McpToolset` using `StreamableHttpServerParameters` with your Vinkius URL. Pass this toolset directly to the `tools` array when building your `LlmAgent`.

You pass a `tool_names` list to the toolset constructor to restrict access. This lets you expose `list_deals` while hiding destructive tools like `remove_contact`.

Gemini ingests massive payloads returned by `list_contacts` and `list_companies`. The agent holds the entire CRM export in its context window for deep reasoning against your Vertex AI models.

Your agent pulls deal IDs using `get_deal_details` and immediately writes that data into your enterprise data warehouse. The ADK handles the orchestration between the MCP tools and your Google Cloud infrastructure.

The server handles sensitive firmographics and deal pipeline values through an encrypted, zero-trust connection. Vinkius authenticates the endpoint token and routes the request without ever logging the underlying Gemini prompts.

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