How to Use the Umami Cloud MCP in Pydantic AI

Q: How does Pydantic AI ensure data quality when using Umami Cloud?

Pydantic enforces type safety at runtime. If the websites tool provides unexpected JSON, the agent fails with a clear validation error instead of proceeding with bad data.

Get guaranteed, type-safe web metrics and user counts using Umami Cloud 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 Cloud MCP to Pydantic AI

Create your Vinkius account to connect Umami Cloud 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 Cloud with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate website metrics from the Umami Cloud MCP Server.

When you call `websites`, your agent gets URLs, browsers, OS, and devices. Before the data hits your logic, Pydantic validates it against a schema. If the API returns garbage, you fail loudly—no silent corruption. The guarantee of correctness means your downstream processes never have to deal with unexpected or hallucinated fields from Umami Cloud.

Ensure type-safe user counts using Pydantic AI.

Use the `users` tool to pull a count. Because this is running through the Pydantic validation layer, you are guaranteed an integer output every single time. You don't have to write extra checks for nulls or strings. This makes your data processing logic cleaner and much more reliable across any model (OpenAI, Gemini, Anthropic).

Process Umami Cloud metrics regardless of the underlying LLM.

The Pydantic AI framework abstracts the connection. You use the same toolset to access `websites` data whether you're running on OpenAI or Gemini. The focus stays on the guaranteed schema, not the model provider. This flexibility means your web analytics pipeline isn't locked into a specific vendor.

Setup guide

Set up Umami Cloud 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-cloud-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Umami Cloud 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 Cloud. 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 Cloud 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 Cloud MCP in Pydantic AI

Pydantic enforces type safety at runtime. If the `websites` tool provides unexpected JSON, the agent fails with a clear validation error instead of proceeding with bad data.

The server exposes detailed data including URLs, browsers, OS, and devices via the `websites` tool. This output is strictly validated against your defined models.

Yes, it's built for correctness. The validation step ensures that every piece of data—like a user count from `users`—is structurally sound before your agent uses it.

The server touches web analytics data, specifically user counts and website metrics (URLs, browsers, OS, devices). This is all validated by your Pydantic models.

Absolutely. The framework is model-agnostic. You can swap out OpenAI for Anthropic or Gemini, but the data contract provided by the MCP Server remains stable.

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