How to Use the Beagle Security MCP in AutoGen

Q: How do I give an AutoGen agent access to the Beagle Security MCP tools?

You pass the tool list generated by the mcpservertools function directly into your AssistantAgent constructor. AutoGen's McpToolAdapter handles the schema conversion, so the agent can see and use the tools in the conversation.

Q: Can multiple AutoGen agents collaborate on a single Beagle Security test?

Yes, that's what it's designed for. One agent can starttest, another can monitor with getteststatus, and a third can gettestresult when it's done. They coordinate their actions through conversation.

Q: Is it possible for one AutoGen agent to start a scan and another to read the Beagle Security results?

Definitely. You would assign the starttest tool to a 'SecurityOperator' agent and the gettestresult tool to a 'SecurityAnalyst' agent. They can then work together, passing the test session ID between them in the chat.

Set up a team of AI agents to debate, manage, and act on your Beagle Security scans using AutoGen.

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 AutoGen

Create your Vinkius account to connect Beagle Security to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Security Operations

This toolset gives your AutoGen agents the functions they need to manage security testing as a team. A 'SecurityManager' agent can be responsible for using `start_test` and `stop_test`, acting on instructions from other agents in the group chat. Meanwhile, a 'QA_Analyst' agent could periodically call `get_test_status` to update the group on progress. This splits responsibilities, letting you build a conversational system where different agents own different parts of the security workflow.

Debate and Decide on Findings

The real power comes from agent conversation. After a test completes, one agent can fetch the report with `get_test_result`. It can present the findings to the group, for example, 'I found 3 critical vulnerabilities.' Another agent, maybe a 'DevOps' persona, could challenge this: 'Are these false positives? What's the impact on performance?' They can debate the severity and decide on a course of action, all based on the data from the Beagle Security MCP Server.

Build a Consensus-Driven AutoGen Workflow

Use AutoGen's group chat to build consensus before taking action. An agent might propose, 'I think we should run a new scan on the 'payment-gateway' application.' It would use `list_applications` to confirm the name is correct. Other agents can agree or disagree. Only when they reach a consensus does the 'SecurityManager' agent actually execute the `start_test` command. This prevents rogue actions and ensures your automated security processes have checks and balances.

Setup guide

Set up Beagle Security MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Beagle Security tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Beagle Security_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Beagle Security data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Beagle Security_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Beagle Security data")
    print(result.messages[-1].content)

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 AutoGen

You pass the tool list generated by the `mcp_server_tools` function directly into your `AssistantAgent` constructor. AutoGen's `McpToolAdapter` handles the schema conversion, so the agent can see and use the tools in the conversation.

Yes, that's what it's designed for. One agent can `start_test`, another can monitor with `get_test_status`, and a third can `get_test_result` when it's done. They coordinate their actions through conversation.

Definitely. You would assign the `start_test` tool to a 'SecurityOperator' agent and the `get_test_result` tool to a 'SecurityAnalyst' agent. They can then work together, passing the test session ID between them in the chat.

Authentication is handled by a single transport token you provide when initializing the client. You don't need to manage separate credentials for each agent in your AutoGen group; the connection handles it for all of them.

The server processes application and project identifiers, test statuses, and vulnerability report data from your Beagle Security account. All traffic is encrypted, and every request is executed in a dedicated, single-use sandbox that is destroyed immediately after.

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