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

Q: How do I index Hotjar (Behavior Analytics) data into a LlamaIndex vector store?

Use the MCP tool spec to fetch tools like listsurveyresponses or listfeedback. Run these tools through your agent, then pass the resulting text documents to your vector index for semantic search.

Q: Can LlamaIndex query specific heatmaps using this Hotjar (Behavior Analytics) MCP Server?

Yes, the agent can call listheatmaps to find the correct ID, then use getheatmap to retrieve the details. The engine can then index this structural data to answer layout questions.

Q: How do I restrict which Hotjar (Behavior Analytics) tools LlamaIndex can access?

You can use the allowedtools filter when initializing the MCP client. This lets you restrict your agent to read-only tools like listsites or getsurvey while blocking others.

Q: Does LlamaIndex support asynchronous calls for fetching session recordings?

Yes, you can use totoollistasync() to load the tools. This ensures your agent can query listrecordings and other behavioral endpoints without blocking your main application loop.

Index Hotjar user feedback and survey responses directly into your LlamaIndex vector store for grounded UX research.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a LlamaIndex knowledge base of user feedback

Stop searching through spreadsheets of customer comments when you can index Hotjar data into LlamaIndex. This MCP Server lets your LlamaIndex agent fetch raw qualitative data using `list_feedback` and `list_survey_responses`. The agent indexes this Hotjar text directly into your LlamaIndex vector store, making user complaints semantically searchable. When you query your LlamaIndex index about onboarding issues, the engine retrieves actual quotes from the Hotjar data, avoiding generic LlamaIndex hallucinations.

Ground UX analysis in live heatmap data

Your LlamaIndex RAG pipelines can now reference live Hotjar visual engagement metrics. By calling `get_heatmap` and `list_heatmaps`, your LlamaIndex engine indexes the actual click and scroll patterns of your web traffic. When building new product specs, your LlamaIndex agent can query this Hotjar index to see which layout elements users ignore. It prevents you from making design decisions that conflict with real Hotjar behavioral data.

Track funnel leaks over time

You can construct a LlamaIndex index of your conversion metrics by calling Hotjar's `list_funnels` on a schedule. The LlamaIndex agent stores these funnel stages, allowing you to ask questions about where users drop out of your Hotjar-tracked checkout flow. The LlamaIndex engine compares current Hotjar funnel data with past indexed runs to flag new bottlenecks. You get a clear, historical view of Hotjar site performance directly in your LlamaIndex workspace.

Setup guide

Set up Hotjar (Behavior Analytics) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Hotjar (Behavior Analytics) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Hotjar (Behavior Analytics) tools.",
)
response = await agent.run("List recent Hotjar (Behavior Analytics) data")

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 LlamaIndex

Use the MCP tool spec to fetch tools like `list_survey_responses` or `list_feedback`. Run these tools through your agent, then pass the resulting text documents to your vector index for semantic search.

Yes, the agent can call `list_heatmaps` to find the correct ID, then use `get_heatmap` to retrieve the details. The engine can then index this structural data to answer layout questions.

You can use the `allowed_tools` filter when initializing the MCP client. This lets you restrict your agent to read-only tools like `list_sites` or `get_survey` while blocking others.

Yes, you can use `to_tool_list_async()` to load the tools. This ensures your agent can query `list_recordings` and other behavioral endpoints without blocking your main application loop.

All survey data fetched via this MCP Server is processed in an ephemeral Vinkius sandbox. The server never writes this feedback to persistent storage, ensuring your customer responses remain private and secure.

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