How to Use the Arize AI MCP in OpenAI Agents SDK

Q: How do I configure Arize AI with OpenAI Agents SDK?

Install openai-agents first. Initialize the server using MCPServerStreamableHttp with your Vinkius endpoint, then pass it into your Agent constructor's mcpservers list.

Q: Can my agent automatically create datasets in Arize AI using OpenAI Agents SDK?

Yes, the agent calls createdataset whenever it identifies outlier interactions. This lets you build test suites from real-world failures without manual exporting.

Q: How does this MCP Server help with Arize AI and OpenAI Agents SDK model drift detection?

Your agent queries getmodel and listspans to compare live production inputs against baseline datasets. If statistical drift exceeds your threshold, the agent flags the project immediately.

Q: What is the fastest way to list active projects?

The agent invokes listprojects directly through the SDK. This returns all active workspaces so your agent knows where to send incoming telemetry.

Watch your ML model performance in real-time by connecting OpenAI Agents SDK directly to your observability dashboards.

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 OpenAI Agents SDK

Create your Vinkius account to connect Arize AI to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track ML drifts using OpenAI Agents SDK

The `get_model` tool exposes live model details directly to your agent's decision loop. When model accuracy drops, the agent detects the shift and pulls relevant logs without human intervention. By adding this MCP server to your agent configuration, you let the SDK automatically trigger checks against production metrics. This setup stops silent failures before they impact your users.

Inspect production traces on the fly

The `list_spans` tool fetches specific execution steps through the MCP interface to help you debug latency spikes inside your agent pipelines. Your agent reads these spans to isolate which LLM call or database query slowed down. Instead of jumping between tools, the agent handles the investigation directly. It pulls execution paths and flags anomalies in your Slack or terminal.

Run automated evaluations with this MCP Server

The `create_dataset` tool lets your agent compile production inputs and outputs into structured test suites. It feeds these directly into your evaluation pipeline to catch regressions early. Using `list_experiments` alongside `list_projects` gives your agent the context it needs to compare runs. You get a clear picture of model performance changes across different system versions.

Setup guide

Set up Arize AI MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Arize AI tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Arize AI tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Arize AI tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Arize AI Agent",
            instructions="You have access to Arize AI tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` first. Initialize the server using `MCPServerStreamableHttp` with your Vinkius endpoint, then pass it into your Agent constructor's `mcp_servers` list.

Yes, the agent calls `create_dataset` whenever it identifies outlier interactions. This lets you build test suites from real-world failures without manual exporting.

Your agent queries `get_model` and `list_spans` to compare live production inputs against baseline datasets. If statistical drift exceeds your threshold, the agent flags the project immediately.

The agent invokes `list_projects` directly through the SDK. This returns all active workspaces so your agent knows where to send incoming telemetry.

All span data and model metrics remain inside your secure V8 sandbox. Vinkius executes these calls without storing your raw ML inputs or API payloads.

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