How to Use the HubSpot Service Hub MCP in Google ADK

Q: How do I configure Google ADK to use the HubSpot Service Hub tools?

Install google-adk via pip. Create a McpToolset using StreamableHttpServerParameters with your endpoint URL. Pass that toolset into your LlmAgent initialization.

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

You restrict exposure using the toolnames filter. If you only want the agent reading data, you expose hssearchtickets and hide the update tools.

Feed your support tickets into Google ADK through our managed MCP Server. Let Gemini read thousands of surveys and manage cases instantly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HubSpot Service Hub MCP to Google ADK

Create your Vinkius account to connect HubSpot Service Hub 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 Service Hub with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search and analyze massive ticket queues

`hs_search_tickets` grabs ticket subjects, pipeline statuses, and creation dates straight from your CRM. Because Gemini handles massive context windows, your agent loads hundreds of open tickets at once. It reads the whole queue in one pass. You combine this with your BigQuery data. The agent matches a customer's support history against their account usage metrics. It then uses `hs_update_ticket` to reassign or escalate the case based on actual product telemetry.

Map support workflows with this MCP Server

`hs_ticket_pipelines` extracts your exact stage labels and internal IDs. Gemini needs these IDs to move tickets around. It pulls the display order so it understands the logical flow from 'New' to 'Closed'. After mapping the stages, the agent triggers `hs_tickets_by_status` to pull every ticket stuck in the queue. It cross-references those cases against recent email logs in your Google Cloud environment to see if the customer replied elsewhere.

Process survey feedback at scale

`hs_list_feedback` dumps your NPS, CSAT, and CES scores directly into the agent's memory. It reads the survey name, the raw rating, and the actual text the customer wrote. This is where the 1M+ token limit matters. You feed months of raw feedback into the model. When it spots a recurring bug complaint, it fires `hs_create_ticket` to open an engineering escalation with all the relevant context attached.

Setup guide

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

Install `google-adk` via pip. Create a `McpToolset` using `StreamableHttpServerParameters` with your endpoint URL. Pass that toolset into your `LlmAgent` initialization.

You restrict exposure using the `tool_names` filter. If you only want the agent reading data, you expose `hs_search_tickets` and hide the update tools.

The agent figures out the required fields from the context. It calls `hs_create_ticket` with a subject, priority, and the correct pipeline ID. The tool returns the new ticket's HubSpot ID instantly.

Your agent runs in your Google Cloud environment. It pulls CRM data via the MCP Server and joins it with your data warehouse records before making decisions.

The server handles sensitive CSAT scores, customer complaints, and pipeline states. Vinkius runs the process in an ephemeral sandbox that dies immediately after execution. We handle the authentication layer, so your Gemini agent just uses one secure endpoint token.

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