How to Use the Aporia MCP in OpenAI Agents SDK

Connect Aporia to the OpenAI Agents SDK to block toxic outputs and track model drift before your production users notice a thing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aporia MCP to OpenAI Agents SDK

Create your Vinkius account to connect Aporia 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 Aporia with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inline safety checks for OpenAI Agents SDK

The `validate_guardrails` tool evaluates your agent's messages for toxicity, PII, and off-topic drift before execution. You pass an array of messages, and this MCP Server immediately returns a pass or fail state. This stops bad outputs dead in their tracks. Instead of waiting for a user report, your production Python agent intercepts the hallucination, triggers a handoff, or rewrites the response based on the strict rules you defined.

Pull real-time drift metrics

The `get_metrics` tool retrieves live performance data for any tracked model in your workspace. You pair this with `get_model` to pull the exact configuration details for the agent currently running. Your multi-agent system uses these numbers to route tasks. If one model starts showing high latency or drift, the agent reads the metrics and shifts the workload to a healthier fallback without human intervention.

Trigger active oversight runs

The `trigger_monitor` tool forces an immediate evaluation of a specific model using your Aporia monitors. You can map available checks using `list_monitors` and `list_dashboards` to see what safety nets are active. This moves observability from a passive dashboard into an active loop. When your agent detects an edge case, it fires off a monitor run instantly, updating your tracing logs with fresh data.

Setup guide

Set up Aporia 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 Aporia tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Aporia 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="Aporia Agent",
            instructions="You have access to Aporia 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 Aporia. 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 Aporia 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 Aporia MCP in OpenAI Agents SDK

Install the openai-agents package via pip. Create an MCPServerStreamableHttp client with your Aporia endpoint and pass it to the mcp_servers array in your Agent constructor.

Yes. Calling the validation tool catches injections and stops the execution flow. Your agent can then safely abort the request.

No. The OpenAI Agents SDK auto-discovers every tool from the MCP Server. Set cacheToolsList=True to speed up initialization.

Most checks resolve in milliseconds. We designed this MCP Server to run inline with your agent logic so you avoid noticeable latency spikes.

Aporia processes the exact message arrays you send through the validation endpoint to check for PII and toxicity. The server only scans the payload in memory and drops it immediately after returning the validation result.

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