How to Use the Hotjar (Behavior Analytics) MCP in OpenAI Agents SDK

Q: Can my OpenAI agent read raw user feedback from Hotjar (Behavior Analytics)?

Yes. The agent uses listfeedback to ingest widget responses. Set cacheToolsList=True to speed up tool discovery during high-volume feedback processing.

Q: Does the OpenAI Agents SDK support handoffs for Hotjar (Behavior Analytics) data?

It does. You configure one agent to monitor listfunnels for drop-offs, which then hands off the context to a second agent that pulls the related listrecordings data to diagnose the issue.

Q: How does this MCP Server handle data privacy for session recordings?

The server processes raw session metadata from listrecordings inside a V8 Isolate Sandbox. The ephemeral container destroys the memory state immediately after your agent receives the payload, ensuring no PII persists in the middleware.

Build production-ready behavior analysis agents using the OpenAI Agents SDK and real user session data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hotjar (Behavior Analytics) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Hotjar (Behavior 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 Hotjar (Behavior Analytics) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Parse session recordings with OpenAI Agents SDK

The `list_recordings` tool pulls raw session data directly into your agent's context window. Instead of manually watching hours of user sessions, your OpenAI agent scans the metadata for rage clicks and rapid scrolling. It correlates these sessions with drop-off points identified by `list_funnels`. Production agents need guardrails before acting on behavioral data. The SDK validates every session pull and traces the agent's reasoning in the OpenAI dashboard. You see exactly why the agent flagged a specific user journey before it triggers an alert to your UX team.

Automate qualitative feedback analysis

Calling `list_survey_responses` feeds unedited customer sentiment straight into your specialized analysis agent. Users type unpredictable things into survey text boxes. Your agent reads these responses, groups them by intent, and pulls the parent configuration using `get_survey` to understand the exact prompt the user saw. Handoffs make this powerful. One agent categorizes the raw survey text, then passes the structured data to a secondary agent that cross-references it with support tickets. The entire pipeline runs autonomously while respecting your predefined safety constraints.

Map click density via MCP Server

The `list_heatmaps` tool gives your agent access to visual engagement metrics across your entire site. When a product manager asks why a feature is failing, the agent executes `get_heatmap` to pull the exact click coordinates and scroll depth for that specific URL. It stops the guessing game. The agent compares the heatmap data against your current UI deployment and highlights dead zones. Because it runs through an MCP connection, the data stays fresh and your agent bases its recommendations on actual user behavior, not assumptions.

Setup guide

Set up Hotjar (Behavior 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 Hotjar (Behavior Analytics) tools at runtime.
3

Create your Agent

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

Install openai-agents via pip. Initialize MCPServerStreamableHttp with your Vinkius endpoint URL and pass it to the mcp_servers array in your Agent constructor.

Yes. The agent uses list_feedback to ingest widget responses. Set cacheToolsList=True to speed up tool discovery during high-volume feedback processing.

It does. You configure one agent to monitor list_funnels for drop-offs, which then hands off the context to a second agent that pulls the related list_recordings data to diagnose the issue.

The SDK's built-in guardrails catch the HTTP 429 errors. Your agent pauses execution and logs the trace in the OpenAI dashboard so you know exactly which tool caused the throttle.

The server processes raw session metadata from list_recordings inside a V8 Isolate Sandbox. The ephemeral container destroys the memory state immediately after your agent receives the payload, ensuring no PII persists in the middleware.

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