How to Use the Umami (Privacy Analytics) MCP in Pydantic AI

Q: How does Umami (Privacy Analytics) interact with the Pydantic AI for attribution?

When you call createattributionreport, the resulting data is instantly validated against your defined Pydantic models. This prevents silent failures, giving you confidence that the report structure is perfect.

Q: Can I manage users and teams using Umami (Privacy Analytics) with the Pydantic AI?

Yes. The agent exposes admin tools like createuser and getteamusers. Even when managing user accounts, the responses are validated, making your administrative workflows rock solid.

Q: What data privacy protections does Umami (Privacy Analytics) offer when using the Pydantic AI?

When using the Pydantic AI framework, the server touches session details. The system validates that only necessary aggregated metrics are returned, ensuring you process clean, structured analytics without needing raw user identifiers.

Q: How reliable are the metrics provided by Umami (Privacy Analytics) using the Pydantic AI?

The reliability is unmatched. Every time your agent calls getwebsitemetrics, the response is forced through a validation check, guaranteeing that the data types and structure match what you coded.

Build validated analytics agents with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Umami (Privacy Analytics) MCP to Pydantic AI

Create your Vinkius account to connect Umami (Privacy Analytics) 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 Umami (Privacy Analytics) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deep Event Tracking and Retrieval

Need to know what happened on a page? You can get all event data grouped by name using `get_website_event_data`. It also pulls specific field counts with `get_website_event_data_fields`. Since the Pydantic AI framework validates every response, you never risk receiving unexpected or corrupted data fields.

Comprehensive Reporting Automation

Stop stitching reports together manually. The Umami (Privacy Analytics) MCP Server handles core reporting functions like generating a full conversion funnel with `create_funnel_report` or calculating revenue over time via `create_revenue_report`. Pydantic ensures the output structure is always correct for your application.

Real-Time Performance Monitoring

Don't wait for daily reports. You can get live statistics within the last 30 minutes using `get_realtime_stats`, or track active users in the last five minutes with `get_website_active`. The Pydantic AI framework makes sure these real-time data streams conform to your expected types.

Setup guide

Set up Umami (Privacy Analytics) 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": {
        "umami-privacy-analytics-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Umami (Privacy Analytics) 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 Umami. 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 Umami (Privacy 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 Umami (Privacy Analytics) MCP in Pydantic AI

When you call `create_attribution_report`, the resulting data is instantly validated against your defined Pydantic models. This prevents silent failures, giving you confidence that the report structure is perfect.

Yes. The agent exposes admin tools like `create_user` and `get_team_users`. Even when managing user accounts, the responses are validated, making your administrative workflows rock solid.

When using the Pydantic AI framework, the server touches `session details`. The system validates that only necessary aggregated metrics are returned, ensuring you process clean, structured analytics without needing raw user identifiers.

You can manage site infrastructure directly through the agent. Tools like `get_website` and `update_website` provide data that is strictly typed, so you know exactly what fields to expect when managing your web properties.

The reliability is unmatched. Every time your agent calls `get_website_metrics`, the response is forced through a validation check, guaranteeing that the data types and structure match what you coded.

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