How to Use the Arize AI MCP in Pydantic AI

Q: How do I integrate Arize AI with Pydantic AI?

Install pydantic-ai-slimmcp and use the unified MCPToolset class pointing to your Vinkius HTTP endpoint. Pass this toolset to your Agent constructor to enable strict validation.

Q: Will Pydantic AI catch errors from Arize AI?

Yes, if tools like getmetrics return unexpected data types, the framework throws a validation error immediately. This prevents hallucinated fields from entering your observability pipeline.

Q: Can I list my Arize AI models using Pydantic AI?

Your agent can call listmodels to retrieve tracked ML models or LLMs. The response is automatically parsed into your defined Python types.

Connect Pydantic AI to the Arize AI MCP Server to enforce strict type validation on your ML observability metrics and evaluation runs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arize AI MCP to Pydantic AI

Create your Vinkius account to connect Arize AI 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 Arize AI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Metrics with Pydantic AI

The `get_metrics` tool fetches observability stats that your agent instantly validates against strict Pydantic schemas. If the platform returns an unexpected field type for data drift, the agent fails loudly instead of silently corrupting your monitoring pipeline. Model definitions require exact specifications. Calling `get_model` retrieves the inputs, outputs, and features, which guarantees your agent works with the exact signature defined in your tracking system.

Type-Safe Log Ingestion

Firing the MCP tool `ingest_log` pushes raw telemetry logs into Arize only after your agent verifies the payload structure. You construct the telemetry data in Python, and the framework guarantees it matches the required format before making the request. Workspaces separate these telemetry datasets. The agent calls `list_spaces` to find the correct destination, completely avoiding silent routing errors caused by bad strings.

Run Evaluations via MCP Server

Using `run_eval` triggers custom checks like PII filtering or hallucination detection. Because Pydantic AI enforces correctness, your agent guarantees the evaluation parameters match the specific model requirements. Finding the right test data is just as strict. The agent uses `list_datasets` and `get_dataset` to load static evaluation records, validating every row before comparing it to your production baselines found via `list_environments`.

Setup guide

Set up Arize AI 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": {
        "arize-ai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install `pydantic-ai-slim[mcp]` and use the unified `MCPToolset` class pointing to your Vinkius HTTP endpoint. Pass this toolset to your Agent constructor to enable strict validation.

Yes, if tools like `get_metrics` return unexpected data types, the framework throws a validation error immediately. This prevents hallucinated fields from entering your observability pipeline.

Your agent can call `list_models` to retrieve tracked ML models or LLMs. The response is automatically parsed into your defined Python types.

The unified toolset approach supports both Streamable HTTP and SSE transports. You just need to provide the external Vinkius server URL.

Vinkius handles the authentication using a single endpoint token while running the MCP connection in a V8 Isolate Sandbox. Your raw telemetry logs and production inferences are processed in a zero-trust environment that spins down instantly after the request.

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