How to Use the Hotjar MCP in Pydantic AI

Q: How do I configure the Hotjar MCP Server with Pydantic AI?

Initialize the MCPToolset with your Vinkius HTTP endpoint and pass it into the Agent constructor's toolsets parameter. This unified approach handles all connections over secure SSE or Streamable HTTP transports.

Q: How do I check if my tracking widgets are active using this setup?

Your agent can call listfeedback to fetch a clean list of active widgets, then use getfeedbackwidget to inspect specific configurations. The framework validates the returned widget states against your defined schemas.

Q: How does this setup protect user email addresses during lookups?

When calling lookupuser, all search queries and returned records are transmitted over an encrypted TLS connection managed by Vinkius. Pydantic AI enforces strict string patterns on email fields, ensuring that sensitive identifier data is never logged in plaintext or exposed to public tracing services.

Fetch type-safe user recordings and heatmaps using Pydantic AI to guarantee clean behavioral 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 MCP to Pydantic AI

Create your Vinkius account to connect Hotjar to Pydantic AI 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 with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Replay Metadata with Pydantic AI

`get_recording` pulls detailed metadata for any user session on your site. This MCP Server tool delivers structured JSON containing session duration, page count, and device properties directly to your agent. Because you are using Pydantic AI, every field in the response is validated against strict schemas at runtime. If the API structure changes or contains unexpected null values, the framework catches it immediately, preventing corrupted data from entering your analytics database.

Parse Survey Answers Safely

`get_survey_stats` extracts quantitative metrics and completion rates from active web surveys. The agent uses this tool to monitor drop-off rates on your feedback widgets. The framework enforces strict type definitions on every metric returned. Your agent can confidently calculate average scores and response counts without risking runtime crashes caused by malformed API payloads.

Safe User Lookups via MCP Server

`lookup_user` searches your tracking database using specific identifiers to find associated sessions and feedback. The agent calls this tool when a customer submits a support ticket, instantly linking their complaint to their actual site experience. This direct lookup bypasses manual search steps in external dashboards. Your support agent gets verified, structured user histories, allowing them to diagnose technical issues on the spot.

Setup guide

Set up Hotjar MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "hotjar-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Hotjar tools.",
)

result = await agent.run("List recent Hotjar transactions")
print(result.output)

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 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 MCP in Pydantic AI

Initialize the `MCPToolset` with your Vinkius HTTP endpoint and pass it into the `Agent` constructor's `toolsets` parameter. This unified approach handles all connections over secure SSE or Streamable HTTP transports.

The framework will fail loudly with a validation error, stopping the agent before it processes corrupted information. This guarantees that tools like `get_recording` only feed clean, correctly formatted data into your application logic.

No, the server must run externally. Vinkius hosts and manages the server instance for you, providing a secure, single-endpoint HTTP token that your local agent connects to over the web.

Your agent can call `list_feedback` to fetch a clean list of active widgets, then use `get_feedback_widget` to inspect specific configurations. The framework validates the returned widget states against your defined schemas.

When calling `lookup_user`, all search queries and returned records are transmitted over an encrypted TLS connection managed by Vinkius. Pydantic AI enforces strict string patterns on email fields, ensuring that sensitive identifier data is never logged in plaintext or exposed to public tracing services.

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