How to Use the Pirsch Analytics MCP in Pydantic AI

Type-safe Pirsch Analytics integration for Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pirsch Analytics MCP to Pydantic AI

Create your Vinkius account to connect Pirsch Analytics 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 Pirsch Analytics with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe statistics with Pydantic AI

Get runtime-validated analytics results in your agents. Every tool like `get_statistics_page` returns data mapped directly to your Pydantic schemas. If the API returns bad data, your agent crashes before it corrupts your logic. It’s the safest way to handle external metrics.

Reliable event logging in Pydantic AI

Use `send_hit` to record traffic with strict schema enforcement. The agent verifies every parameter before dispatching it to the backend. You stop guessing if your tracking calls are formatted correctly. Pydantic AI ensures every event matches your expected data structure.

Control domains with Pydantic AI

Register and monitor your domains using validated tool calls. `create_domain` ensures your domain setup follows your strict internal configuration models. It removes the risk of misconfigured tracking endpoints. You get consistent, predictable state management across all your projects.

Setup guide

Set up Pirsch 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": {
        "pirsch-analytics-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Pirsch 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 Pirsch Analytics. 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.