How to Use the Intruder MCP in AutoGen

Q: How do AutoGen agents use the Intruder MCP Server to resolve issues?

One agent fetches vulnerability details using getissue. It passes this data to a developer agent, who proposes a fix and verifies it against the target metadata from gettarget.

Q: Can AutoGen agents trigger new Intruder scans automatically?

No, this server focuses on auditing. Agents use listscans and getscan to monitor results, ensuring they only act on verified, completed security assessments.

Q: Can AutoGen agents manage my Intruder licenses?

Yes, agents can call listlicences to audit your subscription capacity. They can alert you if your active target count is approaching your licensed limit.

Q: Is my sensitive Intruder account information safe with AutoGen?

Yes, your account details fetched via getaccount are processed in a zero-trust, ephemeral MCP sandbox on Vinkius, ensuring your API keys and security posture remain private.

Deploy debating AutoGen agents to negotiate security risk, analyze Intruder scans, and coordinate patches.

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 AutoGen

Create your Vinkius account to connect Intruder 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 Intruder with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents debate Intruder vulnerabilities

The `list_issues` tool fuels multi-agent debates about patch prioritization. A security agent pulls critical issues, while a developer agent argues for sprint velocity, using data from `get_issue` to negotiate which flaws demand immediate downtime. This consensus-driven approach stops automated alert fatigue. By analyzing the vulnerability context together, the agents agree on a remediation plan before presenting a single, high-confidence ticket to your human team.

Reconcile cloud targets using AutoGen and MCP

The `list_targets` tool allows your AutoGen agents to audit your active infrastructure. One agent pulls your cloud inventory using `list_cloud_integrations`, while another checks the active target list to find untracked servers. When they find a discrepancy, they call `get_target` to pull metadata and debate the risk. Flagging the unmonitored asset becomes a coordinated effort, ensuring your attack surface remains fully mapped without manual oversight.

Coordinate multi-team patch campaigns in AutoGen

The `list_teams` tool lets your agents map security issues to ownership groups. When `list_scans` reveals a failed scan, a coordinator agent assigns the cleanup task to the specific engineering team responsible for that asset. To ensure the team has capacity, the agent checks `list_licences` before they spin up new test targets. Monitoring their progress happens in the background by polling `get_scan` until the security issue is verified as resolved.

Setup guide

Set up Intruder 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 Intruder 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="Intruder_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Intruder 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="Intruder_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Intruder 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 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 AutoGen

One agent fetches vulnerability details using `get_issue`. It passes this data to a developer agent, who proposes a fix and verifies it against the target metadata from `get_target`.

No, this server focuses on auditing. Agents use `list_scans` and `get_scan` to monitor results, ensuring they only act on verified, completed security assessments.

Pass the server URL to StreamableHttpServerParams and use mcp_server_tools to fetch the tools. The McpToolAdapter automatically maps the schemas for your AssistantAgent.

Yes, agents can call `list_licences` to audit your subscription capacity. They can alert you if your active target count is approaching your licensed limit.

Yes, your account details fetched via `get_account` are processed in a zero-trust, ephemeral MCP sandbox on Vinkius, ensuring your API keys and security posture remain private.

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