How to Use the Hotjar (Behavior Analytics) MCP in Vercel AI SDK

Q: Can I build a real-time analytics dashboard with this setup?

Yes. Your AI client uses tools like listfeedback and listsurveyresponses, and the Vercel SDK's streaming features pipe that data right into your UI. It's built for live monitoring.

Q: What's the setup process for Hotjar (Behavior Analytics) and the Vercel AI SDK?

Install the npm packages and use createMCPClient with your Vinkius URL. You get the tools by calling mcpClient.tools() and pass them to generateText or streamText. You can get started in a few lines of code.

Stream Hotjar analytics into your Vercel AI SDK app. Watch user behavior data appear live in your UI, no spinners.

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 Vercel AI SDK

Create your Vinkius account to connect Hotjar (Behavior Analytics) to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live User Session Insights

Connect your agent to this MCP server and have it feed user session data directly into your frontend. Your Vercel AI SDK app can call `list_recordings` and stream the results right into a custom React component, giving you a live look at user activity. This isn't just about dashboards. You can build UIs where a product manager literally asks, "Show me recent sessions where users failed to check out," and the corresponding recordings from `list_recordings` populate a list in real time. It closes the gap between data and action.

Visualize Engagement with the Vercel AI SDK

Go beyond static reports. Your AI client can use `list_heatmaps` to find the right visualization and `get_heatmap` to fetch its data. The Vercel AI SDK then streams that data directly to your frontend. Imagine a component that renders a heatmap overlay on a page screenshot, with the data filling in live as the AI client provides it. Your users can ask for heatmaps by name or URL and see the results build right in front of them. That's interactive analysis, not a stale PDF.

Process Qualitative Feedback Instantly

Turn raw user feedback into a structured, real-time feed. Your agent can use `list_surveys` and `list_feedback` to find relevant user comments, then pull the details with `list_survey_responses`. With the Vercel AI SDK, you can build a component that shows new survey responses as they're processed by the agent. A support lead could ask the AI to find all one-star feedback from the last 24 hours, and the answers stream onto their screen, ready for follow-up.

Setup guide

Set up Hotjar (Behavior Analytics) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Hotjar (Behavior Analytics) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Hotjar (Behavior Analytics) transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You connect the server to your Vercel AI SDK client with one Vinkius endpoint token. Your agent can then call tools like `list_recordings`, and the SDK streams the data directly into your React or Next.js components.

Yes. Your AI client uses tools like `list_feedback` and `list_survey_responses`, and the Vercel SDK's streaming features pipe that data right into your UI. It's built for live monitoring.

Install the npm packages and use `createMCPClient` with your Vinkius URL. You get the tools by calling `mcpClient.tools()` and pass them to `generateText` or `streamText`. You can get started in a few lines of code.

This server provides read-only access to your Hotjar data. Your agent can analyze what's there using tools like `get_heatmap` and `list_funnels`, but it can't change anything in your Hotjar account.

Your Vinkius token authenticates every request. The server only fetches the data your agent asks for, like user session details from `list_recordings`. All connections are ephemeral and run in a zero-trust sandbox, isolating your credentials and the data in transit.

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