How to Use the HubSpot Marketing Hub MCP in OpenAI Agents SDK

Q: How do I connect HubSpot Marketing Hub to OpenAI Agents SDK?

Install openai-agents and define an MCPServerStreamableHttp connection. Pass the Vinkius MCP Server endpoint URL and your token to the agent constructor. The framework auto-discovers the six available tools.

Q: Does OpenAI Agents SDK know which HubSpot Marketing Hub emails are drafts?

Yes. The hslistmarketingemails tool returns the current state of each email. Your agent sees exactly which messages are published, sent, or still in draft mode.

Q: How fast is the tool discovery process?

Tool discovery happens on initialization. Set cacheToolsList=True in your parameters to bypass repeated discovery calls and speed up agent startup times.

Connect HubSpot Marketing Hub to OpenAI Agents SDK to build production agents that read your campaign data safely.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HubSpot Marketing Hub MCP to OpenAI Agents SDK

Create your Vinkius account to connect HubSpot Marketing Hub 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 Marketing Hub with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Campaign Audits via MCP Server

The `hs_list_campaigns` tool pulls initiative names, statuses, and dates directly into your OpenAI agent. You build multi-agent handoffs where one agent reads active campaigns and passes the context straight to a reporting agent. Tracing catches every read request. When your system checks `hs_list_marketing_emails` to see which drafts are pending, the dashboard logs the exact payload. Your marketing operations team knows exactly what the agent sees.

Form Performance Tracking

Use `hs_list_forms` to find the exact ID for your lead capture assets before checking their volume. Your agent grabs the form ID, then immediately calls `hs_form_submissions` to read the visitor field values and submission dates. Built-in guardrails validate these actions before execution. If an agent tries to pull submissions for a nonexistent form, the framework catches the error. You get a reliable data pipeline instead of hallucinated leads.

Audience Segmentation Analysis

The `hs_list_contact_lists` tool returns the names, types, and contact counts for your smart and manual lists. Your agent reads the dynamic list sizes to determine which segment has enough contacts for a new push. You pair this with `hs_list_landing_pages` to verify where those lists are sent. The agent checks the publish status and public URL, ensuring the target page is live before the campaign launches.

Setup guide

Set up HubSpot Marketing Hub 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 Marketing Hub tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives HubSpot Marketing Hub 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 Marketing Hub 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 Marketing Hub Agent",
            instructions="You have access to HubSpot Marketing Hub 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 Marketing 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 Marketing Hub MCP in OpenAI Agents SDK

Install `openai-agents` and define an `MCPServerStreamableHttp` connection. Pass the Vinkius MCP Server endpoint URL and your token to the agent constructor. The framework auto-discovers the six available tools.

No. This MCP Server only provides read access to existing assets. Your agent lists items and reads form submissions, but it cannot write new records.

Yes. The `hs_list_marketing_emails` tool returns the current state of each email. Your agent sees exactly which messages are published, sent, or still in draft mode.

Tool discovery happens on initialization. Set `cacheToolsList=True` in your parameters to bypass repeated discovery calls and speed up agent startup times.

Visitor field values pass through a V8 Isolate Sandbox. Vinkius destroys the ephemeral environment immediately after the MCP request finishes. No contact data persists on the middleware layer.

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