How to Use the Hotjar (Behavior Analytics) MCP in Google ADK

Q: Can I restrict which Hotjar (Behavior Analytics) tools the Google ADK exposes?

Yes. You use the toolnames filter in the McpToolset configuration to limit the agent to specific operations like getheatmap while blocking listrecordings.

Q: Can I pipe Hotjar funnel data directly into BigQuery?

Your agent extracts the drop-off metrics using listfunnels and formats them into a schema that matches your BigQuery tables. You write the insertion logic in your native GCP pipeline.

Q: Is PII from survey responses secure during MCP execution?

The connection isolates listsurveyresponses payloads within a zero-trust execution environment. Vinkius requires only one endpoint token, and the ephemeral network tunnel closes the second Gemini finishes reading the text.

Feed raw user behavior data into Gemini's massive context window using the Google ADK.

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 Google ADK

Create your Vinkius account to connect Hotjar (Behavior Analytics) to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ingest feedback widgets into Google ADK

The `list_feedback` tool extracts raw user comments from your on-page widgets. Your Gemini agent queries `list_sites` to map these comments to specific domains, then dumps the structured output directly into BigQuery for long-term storage. Gemini's massive context window changes how you process this text. Instead of summarizing feedback in small chunks, your agent loads thousands of raw responses at once. It finds obscure patterns connecting a bug report in Germany to a UI complaint in Japan.

Analyze conversion drops via MCP Server

Executing `list_funnels` pulls your exact conversion drop-off percentages into your Vertex AI environment. When the agent spots a 40% drop at checkout, it immediately calls `list_recordings` to fetch the metadata for those specific failed sessions. You don't need manual UX researchers clicking through dashboards. The agent cross-references the recording timestamps with your Google Cloud application logs. It tells you if users abandoned the cart because of confusing UX or a backend latency spike.

Cross-reference user sentiment at scale

The `list_surveys` tool retrieves all active survey configurations across your product. Your agent follows up by running `list_survey_responses` to pull the actual answers users submitted regarding their experience. Running this through the Google ADK means you integrate behavioral data with enterprise infrastructure. The agent takes the survey responses, analyzes the sentiment using Gemini, and triggers a Vertex pipeline to adjust your marketing copy based on the findings.

Setup guide

Set up Hotjar (Behavior Analytics) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Hotjar (Behavior Analytics) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Hotjar (Behavior Analytics)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Hotjar (Behavior Analytics) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the google-adk package. Wrap your Vinkius URL in StreamableHttpServerParameters, pass it to McpToolset, and assign it to the tools list in your LlmAgent.

Yes. You use the tool_names filter in the McpToolset configuration to limit the agent to specific operations like get_heatmap while blocking list_recordings.

The 1M+ token context window allows your agent to ingest thousands of list_survey_responses returns simultaneously. It processes the entire dataset in a single prompt without chunking.

Your agent extracts the drop-off metrics using list_funnels and formats them into a schema that matches your BigQuery tables. You write the insertion logic in your native GCP pipeline.

The connection isolates list_survey_responses payloads within a zero-trust execution environment. Vinkius requires only one endpoint token, and the ephemeral network tunnel closes the second Gemini finishes reading the text.

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