How to Use the Beagle Security MCP in OpenAI Agents SDK

Q: How do I stop a test through the OpenAI Agents SDK?

Invoke the stoptest tool when your logic detects a critical failure. It shuts down the specific session immediately without manual intervention.

Run Beagle Security tests directly from your OpenAI Agents SDK code with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Beagle Security MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger vulnerability scans via OpenAI Agents SDK

Your agent kicks off security audits by calling `start_test`. This bypasses manual dashboards and keeps your testing pipeline inside your Python codebase. Once the test initiates, your agent tracks progress using `get_test_status`. It ensures your production system waits until the scan completes before proceeding to deployment.

Fetch test results for automated validation

The agent pulls raw security findings using `get_test_result`. You get the full JSON output directly into your agent's context for immediate analysis. Because you're using this MCP Server, your agent can compare current vulnerabilities against past benchmarks. It uses `get_test_sessions` to verify if the latest build introduced any new regressions.

Manage your security projects programmatically

List all your active targets with `list_applications` to ensure the agent is scanning the correct environment. It prevents accidental tests on staging servers by checking project IDs first. Use `get_application` to grab metadata for specific instances. This provides your agent with the necessary context to decide if a high-severity alert requires an immediate stop via `stop_test`.

Setup guide

Set up Beagle 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 Beagle Security tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Beagle 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 Beagle 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="Beagle Security Agent",
            instructions="You have access to Beagle 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 Beagle 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 Beagle 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 Beagle Security MCP in OpenAI Agents SDK

Define the server using MCPServerStreamableHttp in your Python script. Pass this instance into your Agent constructor's mcp_servers list for automatic tool discovery.

Yes, you can register these nine security tools alongside your other functions. Enable cacheToolsList to keep your agent's response latency low during execution.

Absolutely. Since your agent validates all tool outputs against your defined schemas, you can force the agent to reject incomplete test results before they hit your logs.

Invoke the `stop_test` tool when your logic detects a critical failure. It shuts down the specific session immediately without manual intervention.

The server only touches your application vulnerability metadata and test status logs. Vinkius manages the connection, ensuring your sensitive scan results stay isolated during the exchange.

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