Can I start a security test for a specific application from the agent?

Yes! Use the `start_test` action with your application's token. Your agent will trigger the penetration test in your Beagle Security account immediately.

How do I check if a running security test has finished?

Simply ask the agent to `get_test_status` with the Test ID. It will return the current phase of the test and its completion status.

Does the integration show me the details of found vulnerabilities?

Yes. Once a test is finished, you can use `get_vulnerabilities` or `get_test_results` to retrieve a list of findings, including severity and descriptions.

Beagle Security MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Beagle Security
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Beagle Security through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Beagle Security Assistant",
            instructions=(
                "You help users interact with Beagle Security. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Beagle Security"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Beagle Security MCP Server

Connect your Beagle Security account to any AI agent and integrate automated penetration testing into your development workflow through natural conversation.

The OpenAI Agents SDK auto-discovers all 10 tools from Beagle Security through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Beagle Security, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Project Oversight — List and manage all security projects and target applications.
On-Demand Testing — Trigger new security tests for your applications instantly.
Status Monitoring — Check the real-time progress of ongoing security assessments.
Vulnerability Retrieval — Access detailed results and lists of vulnerabilities found during tests.
Compliance & Auditing — Retrieve account profiles and test histories for compliance reporting.

The Beagle Security MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Beagle Security to OpenAI Agents SDK via MCP

Follow these steps to integrate the Beagle Security MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Beagle Security

Why Use OpenAI Agents SDK with the Beagle Security MCP Server

OpenAI Agents SDK provides unique advantages when paired with Beagle Security through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Beagle Security + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Beagle Security MCP Server delivers measurable value.

Automated workflows: build agents that query Beagle Security, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Beagle Security, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Beagle Security tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Beagle Security to resolve tickets, look up records, and update statuses without human intervention

Beagle Security MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Beagle Security to OpenAI Agents SDK via MCP:

get_application_details

Get details of an application

get_project_details

Get details of a specific project

get_test_results

Retrieve security test results

get_test_status

Check status of a security test

get_user_profile

Get Beagle account profile

get_vulnerabilities

List vulnerabilities for a test

list_applications

List security applications

list_projects

List Beagle Security projects

start_test

Start a new security test

stop_test

Stop an active security test

Example Prompts for Beagle Security in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Beagle Security immediately.

"List all my current security projects on Beagle."

"Start a new security test for application token app_998877."

"Show me the findings from the last test test_554433."

Troubleshooting Beagle Security MCP Server with OpenAI Agents SDK

Common issues when connecting Beagle Security to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Beagle Security + OpenAI Agents SDK FAQ

Common questions about integrating Beagle Security MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.