How to Use the Outlier Detection Engine MCP in Pydantic AI

Type-safe statistical anomaly detection for Pydantic AI agents running critical data pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Outlier Detection Engine MCP to Pydantic AI

Create your Vinkius account to connect Outlier Detection Engine 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 Outlier Detection Engine with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-Safe MCP Server Integration for Pydantic AI

Stop worrying about your agent passing malformed data to statistical functions. Pydantic AI validates every single input and output against strict schemas before the `detect_outliers` tool ever runs on the server. If your model tries to pass text to a column that expects floats, the framework catches it instantly. This prevents runtime crashes in your data processing pipelines.

Deterministic IQR and Z-Score Validation

This MCP Server replaces LLM guesswork with hard math. By exposing the `detect_outliers` tool to your agent, you ensure that statistical boundaries are calculated using strict, reproducible formulas. The output is returned as a validated Pydantic model. Your agent can immediately parse the list of outliers without risking silent data corruption or hallucinated fields.

Unified MCPToolset Setup

Set up the connection using the modern MCPToolset class pointing to your server URL. This unified approach handles all the underlying SSE transport details automatically. Pass the toolset directly to your Agent constructor. Your agent gets instant access to deterministic calculations while maintaining complete model-agnostic flexibility.

Setup guide

Set up Outlier Detection Engine 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": {
        "outlier-detection-engine-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Outlier Detection Engine 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 simple-statistics. 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 Outlier Detection Engine 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 Outlier Detection Engine MCP in Pydantic AI

The Pydantic AI framework automatically maps the JSON output of the `detect_outliers` tool to a typed Python object. If the server returns unexpected data formats, the framework raises a loud validation error immediately.

Yes. Since the MCP Server runs the IQR and Z-Score math locally, your Pydantic AI agent only handles the structured input and output schemas. This keeps memory usage low even when processing thousands of rows.

Writing custom validators for complex statistical math like IQR requires heavy boilerplate. This MCP Server gives you a pre-built, optimized `detect_outliers` tool that works out of the box with any model.

Yes. You can connect your Pydantic AI agent to the server using the MCPToolset over Server-Sent Events (SSE). It provides a stable, long-lived connection for continuous data streaming.

All statistical calculations occur within a secure, ephemeral V8 isolate on Vinkius. Your raw numbers are processed in memory and immediately discarded, ensuring zero persistent storage of your dataset.

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