How to Use the Arize AI MCP in OpenAI Agents SDK

Q: How do I connect Arize AI to OpenAI Agents SDK?

Install openai-agents via pip and create an MCPServerStreamableHttp instance with your Vinkius endpoint URL. Pass it to your Agent constructor using the mcpservers parameter to auto-discover the tools.

Q: Can OpenAI Agents SDK read my Arize AI metrics?

Yes, the agent can call getmetrics to pull observability data. You can set cacheToolsList=True to speed up tool discovery during these metric checks.

Q: What traces does Arize AI support with OpenAI Agents SDK?

You can push raw logs using the ingestlog tool. The agent formats the payload structure and sends it to your configured workspace, which you can locate first using listspaces.

Q: How do I trigger evaluations from my agent?

Call runeval to start a specific check like hallucination filtering. The agent waits for the run to complete and can pull the results back into your OpenAI dashboard trace.

Connect OpenAI Agents SDK to the Arize AI MCP Server to trace agent telemetry and trigger automated LLM evaluations right from your production code.

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 Telemetry with OpenAI Agents SDK

The `ingest_log` tool lets your agent push raw telemetry logs straight into Arize during execution. Your production agent system needs to record every prompt and completion to catch hallucinations before users do. Handoffs between specialized agents generate complex traces that require dedicated observability. You pass the log structure, and the agent records the exact inputs and outputs without breaking its workflow.

Fetch Model Metrics Programmatically

Calling `get_metrics` pulls observability metrics for any tracked ML model directly into your agent's context window via this MCP integration. This means your monitoring agent can check data drift stats and alert a human when performance drops. You also need baseline data to understand those metrics. The `get_model` tool retrieves the specific inputs, outputs, and features defined for that model so your agent knows exactly what it is looking at.

Automate Evaluations via MCP Server

Using `run_eval` triggers a custom LLM evaluation run directly from your agent logic. Your guardrails validate the action, which means the agent only runs approved checks like toxicity filtering against the right datasets. Finding the correct baseline is simple. The agent calls `list_datasets` and `get_dataset` to load static evaluation sets, then maps them against the current production environment using `list_environments`.

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` via pip and create an `MCPServerStreamableHttp` instance with your Vinkius endpoint URL. Pass it to your Agent constructor using the `mcp_servers` parameter to auto-discover the tools.

Yes, the agent can call `get_metrics` to pull observability data. You can set `cacheToolsList=True` to speed up tool discovery during these metric checks.

You can push raw logs using the `ingest_log` tool. The agent formats the payload structure and sends it to your configured workspace, which you can locate first using `list_spaces`.

Call `run_eval` to start a specific check like hallucination filtering. The agent waits for the run to complete and can pull the results back into your OpenAI dashboard trace.

Vinkius runs the Arize MCP connection inside an ephemeral V8 Isolate Sandbox. Your model inferences and evaluation datasets never touch local disk, and the zero-trust architecture destroys the container immediately after the agent finishes its task.

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