How to Use the HubSpot MCP in OpenAI Agents SDK

Q: How do I connect the HubSpot MCP Server to the OpenAI Agents SDK?

Install the package with pip and initialize MCPServerStreamableHttp with your Vinkius endpoint URL. Pass the server instance to the mcpservers array in your Agent constructor. Set cacheToolsList=True to speed up tool discovery.

Q: Can the OpenAI Agents SDK update existing HubSpot deals?

Your agents read deal data using getdealdetails and manage associations using linkcrmobjects. They also fetch company context via getcompanyinfo to inform routing decisions.

Q: Does the HubSpot integration support OpenAI Agents SDK handoffs?

Yes. One agent runs searchcontacts and passes the resulting IDs to a secondary agent. The second agent then executes getcontactdetails without losing context.

Give your OpenAI Agents SDK production-ready read and write access to your HubSpot CRM pipelines.

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 OpenAI Agents SDK

Create your Vinkius account to connect HubSpot to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync pipelines with OpenAI Agents SDK

Your deployed agents hit the HubSpot MCP Server with `list_deals` to pull live sales pipelines straight into their context window. You set the strict guardrails in the OpenAI Agents SDK. The agent respects them while fetching the current quarter's pipeline data. If the agent needs actual numbers, it fires `get_deal_details` for specific amounts and close dates. Your OpenAI dashboard logs every single CRM ping. You always know exactly what your production system is doing.

Automate contact lifecycle management

The HubSpot integration gives your agents tools to manage the entire customer journey, starting with `create_contact`. Handoffs between specialized agents work perfectly here. A lead qualification agent finds a prospect using `search_contacts` and passes the ID to an operations agent. That operations agent binds the new lead to an existing business account using `link_crm_objects`. If a contact opts out, the agent executes `remove_contact`. Everything stays within the safety constraints you defined in Python.

Audit CRM schemas dynamically via MCP

Your agent uses `get_object_schema` to map out custom fields before attempting any data writes. This stops failed API calls dead in their tracks when sales operations inevitably changes the required properties on a deal record. Once the agent understands the current structure, it pulls the matching owner IDs with `list_hubspot_users`. You get a self-healing system. It adapts to CRM changes without requiring manual SDK updates.

Setup guide

Set up HubSpot MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all HubSpot tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives HubSpot tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate HubSpot tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="HubSpot Agent",
            instructions="You have access to HubSpot tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package with pip and initialize `MCPServerStreamableHttp` with your Vinkius endpoint URL. Pass the server instance to the `mcp_servers` array in your Agent constructor. Set `cacheToolsList=True` to speed up tool discovery.

Your agents read deal data using `get_deal_details` and manage associations using `link_crm_objects`. They also fetch company context via `get_company_info` to inform routing decisions.

Yes. One agent runs `search_contacts` and passes the resulting IDs to a secondary agent. The second agent then executes `get_contact_details` without losing context.

You enforce strict guardrails in the OpenAI dashboard before granting access to `remove_contact`. The SDK validates every intended action against your safety constraints before executing the tool.

The server processes contact names, email addresses, and deal amounts strictly in memory through the V8 Isolate Sandbox. Vinkius drops the ephemeral container the moment your script finishes, leaving no persistent data behind.

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