How to Use the HubSpot CRM (Full) MCP in Google ADK

Q: How do I connect the HubSpot CRM (Full) MCP server to an agent built with Google ADK?

You'll instantiate an McpToolset in your Python code, pointing it to the Vinkius server URL for this MCP server. Then, just pass that toolset into your LlmAgent's tools parameter.

Q: How do I create a deal in a specific sales pipeline?

First, use the hslistpipelines tool to find the pipelineid for the pipeline you want. Then, call hscreatedeal and include that ID in the parameters. If you omit it, the deal will just go to your default pipeline.

Connect your Gemini-powered agents to HubSpot using the Google ADK and act on your CRM data directly from your Google Cloud environment.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HubSpot CRM (Full) MCP to Google ADK

Create your Vinkius account to connect HubSpot CRM (Full) 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 CRM (Full) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Full-Spectrum CRM Record Management

Give your Google ADK agent a complete set of HubSpot operations. It can create new leads with `hs_create_contact`, open sales opportunities with `hs_create_deal`, and even file customer issues with `hs_create_ticket`. Your agent can handle the entire record lifecycle from a single prompt. This isn't just about creation. The agent can search for existing records first using tools like `hs_search_companies` to avoid creating duplicates. It’s a straightforward way to keep your HubSpot data clean while automating tasks.

Query HubSpot from Google ADK

Pull live HubSpot data directly into your Google Cloud workflow. Your agent can use `hs_search_deals` to get a list of opportunities closing this quarter or `hs_search_contacts` to find every contact at a specific company. The data is returned in a structured format, ready for analysis. Because Gemini models in the Google ADK can handle large contexts, your agent can pull extensive data—like the results of multiple searches—and reason over it. It can summarize pipeline health or identify at-risk deals based on the data it gets from this MCP toolset.

Map Your CRM's Internal Structure

Before an agent can assign records or move deals, it needs to understand your setup. The `hs_list_owners` tool lets the agent get a current list of all users in your HubSpot account, so it knows who can be assigned to a new contact or deal. Similarly, `hs_list_pipelines` provides a blueprint of your sales and support processes. The agent can see every stage, from 'Appointment Scheduled' to 'Closed Won', and use the correct IDs when creating new records. This makes your automations much more reliable.

Setup guide

Set up HubSpot CRM (Full) 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 CRM (Full) 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 CRM (Full)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to HubSpot CRM (Full) 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 CRM (Full) 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 CRM (Full) MCP in Google ADK

You'll instantiate an `McpToolset` in your Python code, pointing it to the Vinkius server URL for this MCP server. Then, just pass that toolset into your `LlmAgent`'s `tools` parameter.

Yes. You can equip a specialized 'sales agent' with tools like `hs_create_deal` and a 'support agent' with `hs_create_ticket`. The Google ADK framework is designed for this kind of agent-to-agent collaboration.

You get a fully managed and maintained toolset without writing any API wrapper code. This MCP server handles authentication, updates, and errors, so you can focus on building your agent's logic, not on HubSpot API maintenance.

First, use the `hs_list_pipelines` tool to find the `pipeline_id` for the pipeline you want. Then, call `hs_create_deal` and include that ID in the parameters. If you omit it, the deal will just go to your default pipeline.

All requests involving your company and contact information are processed in a zero-trust, ephemeral environment. The connection is encrypted end-to-end, and we don't log or persist any of the actual CRM data that passes through the server.

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