How to Use the Beagle Security MCP in OpenAI Agents SDK

Q: What's the setup for Beagle Security with the OpenAI Agents SDK?

It's straightforward. After you pip install openai-agents, you'll create an MCPServerStreamableHttp instance pointing to your Vinkius endpoint URL. Pass that into your Agent constructor, and the tools are auto-discovered.

Build production-ready security agents with the OpenAI Agents SDK. Kick off Beagle Security tests and get results 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

Kick Off Security Scans from Code

Your agent can start and stop security scans on its own. Give it a project and application ID, and it will use `start_test` to begin a new scan in Beagle Security. No more manual clicking in a web UI. Need to check on things? The agent can call `get_test_status` to see if a test is running, queued, or finished. If a test needs to be cut short, it can use `stop_test`. The OpenAI SDK's guardrails mean you can set rules on which agent is allowed to stop a test, preventing mistakes.

Get Vulnerability Reports

This MCP Server lets your agent pull detailed security findings directly from Beagle. After a test completes, the agent can use `get_test_results` to get the high-level summary. For a deeper look, your agent can call `get_vulnerabilities` with a specific test ID. It gets back a structured list of every issue found. You can then hand this data off to another specialized agent for reporting or ticket creation in your issue tracker.

Manage Projects with the OpenAI Agents SDK

Your agent can get the lay of the land inside your Beagle Security account. It starts by calling `list_projects` to see all available projects and `list_applications` for the apps inside them. From there, it can drill down with `get_project_details` and `get_application_details` to get specific metadata. This is great for building autonomous agents that can map out your security landscape before deciding which tests to run.

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

You define the rules, the SDK enforces them. The Beagle Security server just exposes the tools, like `start_test`. You configure the guardrails in your OpenAI Agent to control which actions it can take, with what parameters, and when.

Yes, that's exactly what it's for. You could have one agent that uses `list_projects` and `start_test` to manage scans, and another that waits for finished tests, calls `get_vulnerabilities`, and then files Jira tickets. The OpenAI Agents SDK is designed for these handoffs.

It's straightforward. After you `pip install openai-agents`, you'll create an `MCPServerStreamableHttp` instance pointing to your Vinkius endpoint URL. Pass that into your `Agent` constructor, and the tools are auto-discovered.

Yes. The MCP Server for Beagle Security is model-agnostic. As long as you're using the OpenAI Agents SDK, you can pair it with any of their models that support tool use, from GPT-4o to older versions.

The server only processes data needed to run the tools. This includes your Beagle Security project names, application IDs, and test results, including vulnerability details. Vinkius processes this data in an ephemeral, sandboxed environment and it's encrypted in transit.

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