How to Use the Hotjar MCP in OpenAI Agents SDK

Q: How do I connect the Hotjar MCP Server to my OpenAI Agents SDK pipeline?

Install openai-agents and initialize MCPServerStreamableHttp with your Vinkius endpoint. Pass the server instance directly into your Agent constructor's mcpservers list, and the SDK will auto-discover all fifteen tools instantly.

Q: Can my agent automatically pull heatmaps using the OpenAI Agents SDK and Hotjar?

Yes. The agent uses listheatmaps to find the correct page ID, then calls getheatmap to retrieve the interaction data. You can set cacheToolsList=True in your SDK configuration to speed up these lookups during high-traffic analysis.

Q: How does the Hotjar integration with OpenAI Agents SDK handle high volumes of survey data?

The server handles pagination out of the box when calling listsurveyresponses. Your agent can process batches of feedback sequentially, preventing context window overflow while analyzing hundreds of responses.

Q: What happens if the Hotjar API goes down?

You can use checkhotjarstatus to verify connectivity before running analytical loops. If the endpoint is unresponsive, the SDK's built-in error handling catches the failure, allowing your agent to pause operations or alert your team.

Q: How does this integration protect sensitive user recordings?

When calling getrecording or lookupuser, the server only accesses data that has already passed through your Hotjar account's IP and text masking rules. Vinkius runs this connection in an isolated sandbox, ensuring decrypted PII never leaks into public logs or unauthorized environments.

Feed real-time user behavior data straight to your OpenAI Agents SDK pipelines to fix UX friction.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hotjar MCP to OpenAI Agents SDK

Create your Vinkius account to connect Hotjar 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 Hotjar with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Isolate Drop-offs with OpenAI Agents SDK

`list_funnels` identifies the exact step where users abandon your checkout path. Your agent calls this tool to pinpoint high-friction pages, then fetches specific recordings with `list_recordings` to see what went wrong. Instead of guessing why conversions dropped, you get immediate, visual proof of UI bugs. The agent routes these specific session replays to your engineering team's Slack queue, cutting down debugging loops from days to minutes.

Read Heatmaps via MCP Server

`get_heatmap` extracts raw click, move, and scroll data directly into your agent's context. This MCP Server tool exposes exactly where users click and how far down they scroll on your landing pages. Your agent processes these coordinate maps to identify dead links or ignored call-to-action buttons. You get a clear list of layout recommendations backed by actual user interaction percentages, not subjective design opinions.

Process Live Survey Responses

`list_survey_responses` pulls verbatim user feedback from your active onsite surveys. The agent uses this tool to scan for recurring complaints, grouping them by customer sentiment without manual sorting. By combining this with `get_survey_stats`, the agent tracks satisfaction trends over time. If a new deployment triggers a spike in negative feedback, the system flags the issue before it impacts your daily revenue.

Setup guide

Set up Hotjar 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 Hotjar tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Hotjar 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="Hotjar Agent",
            instructions="You have access to Hotjar 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 Hotjar. 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 Hotjar 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 Hotjar MCP in OpenAI Agents SDK

Install `openai-agents` and initialize `MCPServerStreamableHttp` with your Vinkius endpoint. Pass the server instance directly into your Agent constructor's `mcp_servers` list, and the SDK will auto-discover all fifteen tools instantly.

Yes. The agent uses `list_heatmaps` to find the correct page ID, then calls `get_heatmap` to retrieve the interaction data. You can set `cacheToolsList=True` in your SDK configuration to speed up these lookups during high-traffic analysis.

The server handles pagination out of the box when calling `list_survey_responses`. Your agent can process batches of feedback sequentially, preventing context window overflow while analyzing hundreds of responses.

You can use `check_hotjar_status` to verify connectivity before running analytical loops. If the endpoint is unresponsive, the SDK's built-in error handling catches the failure, allowing your agent to pause operations or alert your team.

When calling `get_recording` or `lookup_user`, the server only accesses data that has already passed through your Hotjar account's IP and text masking rules. Vinkius runs this connection in an isolated sandbox, ensuring decrypted PII never leaks into public logs or unauthorized environments.

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