Can my AI automatically trigger a hallucination evaluation on a new dataset?

Yes! You can ask your agent to retrieve the specific Ground Truth dataset ID, formulate a testing payload, and invoke the `run_eval` tool natively. Arize will process the asynchronous scoring internally and log the evaluation securely.

How can I quickly check if a production model is experiencing data drift?

Just tell your agent: 'Fetch the primary metrics for model X'. The AI uses the `get_metrics` query to immediately surface latency degradation, prediction drift flags, and incoming data quality indexes without opening the browser.

Is it possible to track telemetry simultaneously for both local development and production environments?

Absolutely. Arize enforces strict separation using Spaces and Environments. You can instruct your AI agent to query the `list_environments` tool, figure out the sandbox ID, and push manual test logs strictly to the sandbox scope during debugging sessions, keeping production metrics clean.

Arize AI MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Arize AI
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Arize AI through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Arize AI "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Arize AI?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Arize AI MCP Server

Connect your Arize AI observability platform to any AI agent and take full control of your Machine Learning and LLM telemetry workflows through natural conversation.

Pydantic AI validates every Arize AI tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Model Monitoring & Metrics — List all tracked ML models, extract deep configuration schemas, and fetch real-time metrics (performance, data quality, and prediction drift)
Evaluation & Alignment — Launch and list automated LLM evaluation runs (e.g., Toxicity, Hallucination, PII filtering) against static datasets and ground truth baselines
Telemetry Ingestion — Push programmatic raw logs, predictions, and inferences straight into Arize for immediate visualization and tracking
Space & Environment Management — Browse organizational spaces and segregated deployment environments (Production, Training, Verification)

The Arize AI MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Arize AI to Pydantic AI via MCP

Follow these steps to integrate the Arize AI MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Arize AI with type-safe schemas

Why Use Pydantic AI with the Arize AI MCP Server

Pydantic AI provides unique advantages when paired with Arize AI through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Arize AI integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Arize AI connection logic from agent behavior for testable, maintainable code

Arize AI + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Arize AI MCP Server delivers measurable value.

Type-safe data pipelines: query Arize AI with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Arize AI tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Arize AI and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Arize AI responses and write comprehensive agent tests

Arize AI MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Arize AI to Pydantic AI via MCP:

get_dataset

Get a specific evaluation dataset

get_metrics

Fetch observability metrics for an ML model

get_model

It defines the inputs, outputs, and features. Get details and metadata for a specific tracked model

ingest_log

payload_json must contain valid Arize payload structures. Ingest raw telemetry logs into Arize

list_datasets

List static evaluation datasets

list_environments

g., Production, Training, Verification) used to segregate model inferences and baseline datasets. List configured environments within Arize

list_evals

g., Toxicity, Hallucination, PII filtering). List automated evaluation runs

list_models

List tracked ML models or LLMs

list_spaces

Spaces separate different models and telemetry datasets. List accessible workspaces within the Arize platform

run_eval

Trigger a custom LLM evaluation run

Example Prompts for Arize AI in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Arize AI immediately.

"List all active Machine Learning models monitored in my workspace."

"Get the evaluation baseline datasets available for our LLM checks."

"Push these 3 mocked prompt responses as telemetry logs to the 'OpenAI-Customer-Service-Bot' model."

Troubleshooting Arize AI MCP Server with Pydantic AI

Common issues when connecting Arize AI to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Arize AI + Pydantic AI FAQ

Common questions about integrating Arize AI MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Arize AI MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.