How to Use the HubSpot Analytics MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle tool caching for the HubSpot Analytics MCP Server?

Set cacheToolsList=True in your agent configuration. This prevents the SDK from repeatedly querying the Vinkius endpoint to discover tools like hslistreports or hsanalyticsviews. It keeps your agent execution fast and lowers latency.

Q: What happens if my agent queries a non-existent report using this MCP Server?

The hslistreports tool returns the actual configured custom reports from your portal. If your agent requests a report name that is not in that list, the tool execution returns an empty result. The agent then reads this response and can ask you for the correct report name.

Get raw HubSpot metrics directly into your OpenAI Agents SDK pipelines without writing custom API integrations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HubSpot Analytics MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track web traffic trends using the OpenAI Agents SDK

`hs_web_analytics` pulls raw session counts, pageviews, and bounce rates directly into your active agent context. Your agent queries this tool to isolate traffic spikes and map them to new contact creation rates over specific date ranges. The OpenAI Agents SDK manages the tool execution loop, feeding these metrics into your specialized marketing agents. You get clean, unhedged traffic data to make immediate budget decisions without manual CSV exports.

Audit email campaign metrics with your agent

`hs_email_analytics` gets delivery rates, open counts, and spam reports for any specific marketing email. This tool gives your agent the exact numbers needed to check deliverability drops before they ruin your next campaign. The SDK handles the handoff between your diagnostic agents, allowing one to pull the email statistics while another drafts the fix. No middleman code is required to pass these specific HubSpot metrics between your specialized models.

Expose contact timelines to this MCP Server

`hs_list_events` exposes the exact interaction history of any contact, company, or deal by pulling page views, form submissions, and meetings. This MCP Server tool requires an object type and ID to return a chronological feed of user actions. OpenAI Agents SDK applies built-in guardrails to these timeline queries, ensuring your agent only requests history for authorized CRM records. You trace every single event request directly through your developer dashboard.

Setup guide

Set up HubSpot Analytics 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 Analytics tools at runtime.
3

Create your Agent

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

Install the SDK via pip, then initialize the server streamable HTTP parameter with the Vinkius endpoint URL. Pass this server instance directly into your Agent constructor using the `mcp_servers` list. The agent automatically discovers all five analytics tools at runtime.

Yes, the SDK supports parallel tool calling. Your agent can call `hs_web_analytics` to check traffic and `hs_email_analytics` to check email performance simultaneously. This speeds up your multi-agent marketing audits.

Set `cacheToolsList=True` in your agent configuration. This prevents the SDK from repeatedly querying the Vinkius endpoint to discover tools like `hs_list_reports` or `hs_analytics_views`. It keeps your agent execution fast and lowers latency.

The `hs_list_reports` tool returns the actual configured custom reports from your portal. If your agent requests a report name that is not in that list, the tool execution returns an empty result. The agent then reads this response and can ask you for the correct report name.

Vinkius runs the server in an ephemeral V8 isolate sandbox where credentials exist only in memory. Your email metrics and timeline events are fetched over encrypted tunnels and never saved to persistent storage.

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