How to Use the Aikido Security MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK connect to Aikido Security?

You just need your Vinkius endpoint URL. The SDK's MCPServerStreamableHttp class handles the connection, and your agent automatically discovers all the Aikido Security tools. Set cacheToolsList=True in production so it doesn't fetch them on every startup.

Build production security agents with Aikido and the OpenAI Agents SDK, with built-in guardrails and full tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aikido Security MCP to OpenAI Agents SDK

Create your Vinkius account to connect Aikido Security 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 Aikido Security with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Compliance Checks

Your agent can now handle compliance reporting. It will use `get_iso_compliance` and `get_soc2_compliance` to check your status against industry standards. The OpenAI SDK's guardrails mean you can trust the agent to run these checks without causing problems. When an audit comes up, you can task a specialized agent to pull all relevant data. It'll use `export_all_issues` for a complete snapshot and `list_custom_rules` to show your specific policies are enforced. All actions are traced in your OpenAI dashboard, so you have a complete record.

Triage Security Issues with your MCP Server

Stop triaging vulnerabilities manually. A discovery agent can monitor your entire stack by calling `list_open_issues` filtered by repository or type. It gives you a constant, real-time view of what needs fixing. When a critical issue is found, your first agent can hand it off to a specialist. This second agent uses `get_issue_group` to dig into the details, pulling all related findings. Because the OpenAI SDK manages the state, the handoff is clean and you don't lose context.

Map Your Attack Surface

Get a complete inventory of your digital footprint. An agent can call `list_code_repositories`, `list_containers`, and `list_cloud_assets` to map out everything Aikido is monitoring. It’s the fastest way to see what you're protecting. You can also have an agent check your configurations. It will use `list_connected_clouds` and `list_webhooks` to confirm your integrations are working. If something is disconnected, your agent can flag it immediately.

Setup guide

Set up Aikido Security 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 Aikido Security tools at runtime.
3

Create your Agent

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

Run the agent

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

You just need your Vinkius endpoint URL. The SDK's `MCPServerStreamableHttp` class handles the connection, and your agent automatically discovers all the Aikido Security tools. Set `cacheToolsList=True` in production so it doesn't fetch them on every startup.

Yes. While the server exposes all tools by default, you can build logic in your agent's code to filter which tools it's allowed to call. The SDK's guardrails can also enforce policies before execution.

The main benefit is trusted autonomy. The OpenAI SDK provides guardrails and tracing, so you can build agents that perform security tasks like checking `get_iso_compliance` without constant supervision. A simple script just calls an API; an agent with an MCP server understands the goal and its available tools.

Yes. Your connection is secured through Vinkius, which handles authentication. The agent only interacts with the Aikido Security API, it doesn't get direct access to your codebase or infrastructure.

This server processes security issue data. This includes vulnerability reports, compliance statuses, and asset inventories from your Aikido account. Your agent's requests and the API's responses are managed within the ephemeral Vinkius sandbox, which isolates the process.

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