How to Use the Matomo MCP in Pydantic AI

Q: How do I initialize the Matomo MCP toolset in Pydantic AI?

Use the unified MCPToolset class pointing to your Vinkius HTTP endpoint. Pass this toolset instance directly into the toolsets argument of your Agent constructor to enable all ten analytics tools.

Validate your Matomo analytics queries at runtime with the type-safe Pydantic AI framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Matomo MCP to Pydantic AI

Create your Vinkius account to connect Matomo 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 Matomo with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate visitor profiles in Pydantic AI.

The `get_visitor_profile` tool fetches detailed user history schemas that are validated at runtime against strict Pydantic models. Your Pydantic AI agent guarantees that every returned field matches your expected types before processing user data. If the server returns an unexpected data format, the framework raises a validation error immediately. This safety net prevents your agent from acting on corrupt analytics profiles or hallucinating user identifiers.

Audit web properties with this MCP Server.

The `get_site_details` tool retrieves configuration metadata for specific web properties registered in your analytics system. This MCP Server parses this JSON payload into a typed Python object, giving your agent compile-time safety when managing multiple domains. Your agent can safely query `list_sites` to map all available web properties. Because the data is strictly typed, you avoid runtime crashes when switching between different tracking IDs.

Track goal metrics safely in Pydantic AI.

The `get_goals` tool retrieves active conversion targets and validates their structural schemas instantly. Your Pydantic AI agent uses these validated goals to calculate conversion rates without risk of type mismatch errors. You can run this validation pipeline against any LLM, whether you use OpenAI, Anthropic, or local models. The framework handles the type constraints, ensuring consistent behavior regardless of the underlying model's reasoning capability.

Setup guide

Set up Matomo 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": {
        "matomo-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Use the unified `MCPToolset` class pointing to your Vinkius HTTP endpoint. Pass this toolset instance directly into the `toolsets` argument of your `Agent` constructor to enable all ten analytics tools.

Pydantic AI validates the response against the tool schema and raises a clear validation error if a required field is missing. This protects your agent from executing logic with incomplete data.

Yes, the framework is model-agnostic. You can run local models to query `get_visits_summary` while relying on Pydantic to enforce strict data types.

Yes, the toolset supports both SSE and Streamable HTTP transports. You can connect your agent to external servers running on remote infrastructure directly.

The framework validates raw visitor IP address data in memory during runtime and discards it immediately after the agent finishes execution. This MCP validation pipeline prevents tracking data from being stored on Vinkius servers or written to local logs.

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