How to Use the Hotjar (Behavior Analytics) MCP in LangChain

Q: Can a LangChain chain use Hotjar (Behavior Analytics) to link session recordings with feedback?

Yes, your agent can inspect incoming complaints via listfeedback and use those details to filter session replays with listrecordings in one continuous execution loop.

Feed Hotjar behavior data directly into your LangChain decision loops to fix broken funnels based on real user actions.

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 LangChain

Create your Vinkius account to connect Hotjar (Behavior Analytics) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step UX analysis in LangChain

Stop guessing why users quit your sign-up flow when you can pass Hotjar metrics directly to LangChain. This MCP Server lets your LangChain agent pull visual data with `get_heatmap` and correlate it with drop-off points from `list_funnels`. Every Hotjar tool execution gets tracked in LangSmith so you can debug the chain's analysis of your site. You will see exactly how the LangChain agent parses the Hotjar heatmap coordinate data before it suggests a UI fix.

Correlate user complaints with session replays

When a user leaves angry feedback, your LangChain chain can automatically grab the Hotjar context. The agent uses `list_feedback` to find recent complaints, then calls `list_recordings` to pull the exact sessions of those frustrated users. By linking these Hotjar tools together, your LangChain pipeline turns vague complaints into clear diagnostic reports. The LangChain agent handles the multi-step Hotjar search, leaving you with a clean list of session recording IDs to watch.

Contextual feedback synthesis

You can build a LangGraph workflow that uses this MCP Server to monitor user sentiment over time. Your workflow starts by calling `list_surveys` to find active campaigns, then uses `list_survey_responses` to extract the latest raw text answers. Instead of reading hundreds of Hotjar comments manually, the LangChain chain groups responses by sentiment. The agent uses `get_survey` to understand the original questions and outputs a prioritized list of user pain points directly to your LangChain dashboard.

Setup guide

Set up Hotjar (Behavior Analytics) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Hotjar (Behavior Analytics) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "hotjar-behavior-analytics-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Hotjar (Behavior Analytics) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install the adapter package and initialize the multi-server client with the Vinkius endpoint. Call `get_tools()` to fetch the Hotjar tools, then pass them directly to your agent constructor.

Yes, your agent can inspect incoming complaints via `list_feedback` and use those details to filter session replays with `list_recordings` in one continuous execution loop.

LangSmith records every tool call, showing you the exact site ID passed to `list_sites` and the raw JSON returned. You can trace why an agent chose a specific heatmap from `list_heatmaps` without guessing.

Yes, you can mix these behavioral tools with database or issue-tracking tools. An agent can discover a drop-off with `list_funnels` and immediately open a ticket in your project management system with the details.

This MCP Server handles only metadata and secure API tokens to access `list_recordings` within the Vinkius sandbox. No raw video files or personally identifiable information are stored on our platform, keeping your user data safe and compliant.

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