How to Use the Piwik PRO MCP in Pydantic AI

Q: How do I integrate Piwik PRO with Pydantic AI?

Install the pydantic-ai-slimmcp package. Initialize an MCPToolset with your Vinkius HTTP URL, then pass it to the toolsets argument when building your Agent.

Q: Should I use MCPServerHTTP for Piwik PRO in Pydantic AI?

No. That class is deprecated. You should use the unified MCPToolset approach to connect to external servers running on Streamable HTTP or SSE transports.

Q: How does Pydantic AI handle Piwik PRO query errors?

If querypiwikanalytics returns data that violates your Pydantic models, the framework throws a validation error immediately. This stops the agent from processing bad analytics data.

Q: Can my agent discover tracking sites automatically?

Yes. It calls listpiwiksites to enumerate all available tracking properties. You can define a Pydantic model to strictly parse the site IDs and names returned.

Build type-safe Piwik PRO analytics pipelines with Pydantic AI and strict runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Piwik PRO MCP to Pydantic AI

Create your Vinkius account to connect Piwik PRO to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Piwik PRO with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Enforce strict schemas via MCP server

Validate complex nested data from `query_piwik_analytics` directly against your Pydantic models. Analytics APIs change constantly, and your agent needs to fail loudly instead of hallucinating metrics. Pydantic AI checks every response from the tool. You get guaranteed type safety when pulling custom reports from the server.

Audit users and dashboards safely

Pulling exact lists of account metadata with `list_piwik_users` requires strict formatting. You want absolute certainty about who has access to what. Your agent calls the tool to get the account roster and checks `list_piwik_dashboards` to see available views. Pydantic AI ensures the returned JSON matches your exact expectations before passing it downstream.

Map goals with this MCP Server

Your agent uses `list_piwik_apps` to pull the current state of your tracking architecture before running any analysis. Conversion setups drift over time. It runs `list_piwik_goals` to extract the active conversion events. This strict sequence ensures your automated reports always use the latest tracking definitions.

Setup guide

Set up Piwik PRO 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": {
        "piwik-pro-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the `pydantic-ai-slim[mcp]` package. Initialize an `MCPToolset` with your Vinkius HTTP URL, then pass it to the `toolsets` argument when building your Agent.

No. That class is deprecated. You should use the unified `MCPToolset` approach to connect to external servers running on Streamable HTTP or SSE transports.

If `query_piwik_analytics` returns data that violates your Pydantic models, the framework throws a validation error immediately. This stops the agent from processing bad analytics data.

Yes. It calls `list_piwik_sites` to enumerate all available tracking properties. You can define a Pydantic model to strictly parse the site IDs and names returned.

The Vinkius architecture relies on ephemeral execution. When your agent pulls user lists or custom analytics JSON, the transaction happens in an isolated container that terminates the moment the data is handed back to your application.

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