How to Use the Intruder MCP in Google ADK

Q: How do I configure the Intruder MCP Server inside Google ADK?

Install the package using pip install google-adk and define the toolset using the MCP server parameters with the HTTP transport. Pass this toolset to your LlmAgent to instantly expose tools like listissues and listtargets to your Gemini model.

Q: Can Google ADK combine Intruder vulnerability data with BigQuery analytics?

Yes, your Gemini agent can call listissues to get active security flaws and write them to BigQuery for historical trend analysis. The agent can then use getissue to pull remediation advice for any recurring critical vulnerabilities.

Q: Can I restrict which Intruder tools the Google ADK agent can access?

Yes, you can use the optional toolnames filter in the McpToolset constructor to limit exposure. For example, you can restrict the agent to read-only tools like listscans and gettarget while blocking access to account settings.

Run enterprise-grade vulnerability audits inside Google ADK using Intruder tools to secure GCP and multi-cloud environments.

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 Google ADK

Create your Vinkius account to connect Intruder to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map cloud integrations to BigQuery via Google ADK

`list_cloud_integrations` pulls your active AWS, Azure, and Google Cloud connections directly into your Gemini agent. The agent cross-references these integrations with infrastructure tables in BigQuery to find unmonitored cloud accounts. Using this MCP Server with the Google ADK allows Gemini to analyze your entire attack surface. The agent pulls active targets using `list_targets` and identifies gaps in your coverage without manual scripting.

Analyze massive vulnerability backlogs in long context

`list_issues` retrieves your entire vulnerability history so Gemini can analyze thousands of security alerts in its 1M-token context window. The agent uses `get_issue` to extract remediation steps and group similar flaws across teams. You set this up by passing the `McpToolset` to your `LlmAgent` in Python. The agent then correlates issue severity with team ownership using `list_teams` to route remediation instructions to the right engineers.

Audit scan compliance across enterprise teams

`list_scans` provides the complete history of security checks, which your Gemini agent audits to ensure compliance with corporate policies. The agent calls `get_scan` to verify that every target was scanned successfully during the maintenance window. This MCP integration lets your Google ADK agent query `list_licences` to verify you have enough seat capacity for new hosts. It handles the entire audit trail autonomously, writing the compliance status directly to your cloud logging systems.

Setup guide

Set up Intruder MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Intruder tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Intruder_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Intruder tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the package using `pip install google-adk` and define the toolset using the MCP server parameters with the HTTP transport. Pass this toolset to your `LlmAgent` to instantly expose tools like `list_issues` and `list_targets` to your Gemini model.

Yes, your Gemini agent can call `list_issues` to get active security flaws and write them to BigQuery for historical trend analysis. The agent can then use `get_issue` to pull remediation advice for any recurring critical vulnerabilities.

Gemini's 1M-token context window allows the agent to process the entire payload from `list_targets` at once. The agent can map every single infrastructure asset to its corresponding scan results from `get_scan` without running out of memory.

Yes, you can use the optional `tool_names` filter in the `McpToolset` constructor to limit exposure. For example, you can restrict the agent to read-only tools like `list_scans` and `get_target` while blocking access to account settings.

Yes, all communication between Google ADK and Intruder occurs through secure HTTP transports managed by Vinkius. Vulnerability payloads and target metadata are processed in memory and are never used to train Google's foundation models.

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