Hotjar MCP Server for Pydantic AIGive Pydantic AI instant access to 15 tools to Check Hotjar Status, Get Feedback Widget, Get Heatmap, and more
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Hotjar through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.
Ask AI about this App Connector for Pydantic AI
The Hotjar app connector for Pydantic AI is a standout in the Customer Support category — giving your AI agent 15 tools to work with, ready to go from day one.
Vinkius delivers Streamable HTTP and SSE to any MCP client
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to Hotjar "
"(15 tools)."
),
)
result = await agent.run(
"What tools are available in Hotjar?"
)
print(result.data)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Hotjar MCP Server
Connect your Hotjar account to any AI agent and access user experience analytics through natural conversation.
Pydantic AI validates every Hotjar tool response against typed schemas, catching data inconsistencies at build time. Connect 15 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
What you can do
- Survey Management — List all surveys, inspect questions and settings, retrieve individual responses, and review aggregate statistics (completion rate, NPS score, trends)
- Feedback Widgets — Browse incoming feedback widgets, inspect rating breakdowns, and review individual user submissions with screenshots
- Heatmaps — List all heatmap snapshots and inspect click, scroll, and move data for specific pages
- Session Recordings — Browse session recordings with duration and page count, and inspect metadata and events for individual sessions
- Conversion Funnels — List all funnels with step-by-step drop-off data for conversion optimization
- User Lookup — Retrieve session history and behavior data for a specific user ID
- Site Management — List all tracked sites configured in your Hotjar account
The Hotjar MCP Server exposes 15 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
All 15 Hotjar tools available for Pydantic AI
When Pydantic AI connects to Hotjar through Vinkius, your AI agent gets direct access to every tool listed below — spanning heatmaps, session-recordings, user-feedback, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.
Verify connectivity
Get feedback widget details
Get heatmap details
Get recording details
Get survey details
Get survey statistics
List feedback widgets
List feedback responses
List funnels
List heatmaps
List recordings
List tracked sites
List survey responses
List surveys
Lookup user
Connect Hotjar to Pydantic AI via MCP
Follow these steps to wire Hotjar into Pydantic AI. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.
Install Pydantic AI
pip install pydantic-aiReplace the token
[YOUR_TOKEN_HERE] with your Vinkius tokenRun the agent
agent.py and run: python agent.pyExplore tools
Why Use Pydantic AI with the Hotjar MCP Server
Pydantic AI provides unique advantages when paired with Hotjar through the Model Context Protocol.
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Hotjar integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your Hotjar connection logic from agent behavior for testable, maintainable code
Hotjar + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Hotjar MCP Server delivers measurable value.
Type-safe data pipelines: query Hotjar with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Hotjar tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Hotjar and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Hotjar responses and write comprehensive agent tests
Example Prompts for Hotjar in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Hotjar immediately.
"Show the NPS survey results and the top feedback submissions this month."
"Show the heatmap data for our pricing page and the conversion funnel from landing to signup."
"Look up user behavior for user ID 'usr_12345' and show their session recordings."
Troubleshooting Hotjar MCP Server with Pydantic AI
Common issues when connecting Hotjar to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiHotjar + Pydantic AI FAQ
Common questions about integrating Hotjar MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.