How to Use the Intruder MCP in OpenAI Agents SDK

Q: How do I connect the Intruder MCP Server to my OpenAI Agents SDK pipeline?

Install the SDK with pip install openai-agents and set up the streamable HTTP server parameters in your Python code. Use the async with context manager to instantiate MCPServerStreamableHttp and pass it directly to your Agent(mcpservers=server) configuration.

Q: Can my OpenAI Agents SDK agent automatically trigger or check scans using Intruder?

Yes, your agent uses listscans to monitor historical runs and getscan to pull the detailed results of any specific run. You can configure specialized agents to hand off the scan analysis to a development-focused agent when new vulnerabilities are detected.

Q: How can I audit target coverage using this setup?

Your agent calls listtargets to get all current assets and cross-references them with listcloudintegrations to ensure your entire cloud footprint is monitored. If an unmapped target is found, the agent uses gettarget to pull its metadata for triage.

Secure your cloud infrastructure by letting the OpenAI Agents SDK automatically scan and triage vulnerabilities using Intruder.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Intruder MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-triage security flaws with OpenAI Agents SDK

`list_issues` retrieves your current vulnerability backlog so your OpenAI agent can prioritize high-severity items. The agent automatically pulls specific details using `get_issue` to determine which targets need immediate remediation. By passing the Intruder MCP Server to your Agent constructor, these security tools become instantly available. The agent uses guardrails to verify vulnerability severity before triggering alerts, ensuring your team only gets pinged for actual critical exposures.

Track scan frequency and history autonomously

`list_scans` tracks exactly when and how your infrastructure is being tested for security gaps. Your agent checks these timestamps to verify that scans run on schedule and uses `get_scan` to analyze the results of each run. This MCP Server integration lets you set up specialized security agents that hand off tasks to one another. An auditing agent can monitor scan histories and pass the details to a remediation agent if a critical vulnerability shows up.

Match cloud integrations to active target lists

`list_cloud_integrations` identifies which AWS, Azure, or Google Cloud environments are currently linked to your Intruder account. Your agent compares this list against your active infrastructure targets retrieved via `list_targets` to find untracked assets. You config this by passing the MCP server to your OpenAI agent with `cacheToolsList=True` to speed up runtime performance. The agent then queries `get_target` to look up specific metadata for any exposed asset it discovers.

Setup guide

Set up Intruder 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 Intruder tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK with `pip install openai-agents` and set up the streamable HTTP server parameters in your Python code. Use the `async with` context manager to instantiate `MCPServerStreamableHttp` and pass it directly to your `Agent(mcp_servers=[server])` configuration.

Yes, your agent uses `list_scans` to monitor historical runs and `get_scan` to pull the detailed results of any specific run. You can configure specialized agents to hand off the scan analysis to a development-focused agent when new vulnerabilities are detected.

The SDK handles tool discovery automatically when you register the server. It exposes all 10 tools, including `list_issues` and `get_issue`, allowing your agent to query vulnerabilities without manual function mapping.

Your agent calls `list_targets` to get all current assets and cross-references them with `list_cloud_integrations` to ensure your entire cloud footprint is monitored. If an unmapped target is found, the agent uses `get_target` to pull its metadata for triage.

Your Intruder API keys and vulnerability details are isolated within the Vinkius V8 sandbox environment. The OpenAI Agents SDK communicates with the server over a secure, single-token HTTP endpoint, ensuring your infrastructure metadata never leaks to public LLM training sets.

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