How to Use the Halo Security MCP in Google ADK

Q: How do I set up Halo Security with the Google ADK?

You initialize the connection using McpToolset with your Vinkius HTTP endpoint URL. Then, you pass this toolset directly to your LlmAgent in your Python environment, exposing the MCP server tools to Gemini.

Q: Is there a way to limit which Halo Security tools Google ADK can access on this MCP server?

Yes, you can use the optional toolnames filter in the ADK McpToolset configuration. This allows you to restrict the agent to read-only tools like listdnsrecords and block active tools like triggerscan.

Connect your Google ADK agents to Halo Security to audit external vulnerabilities and manage assets using Gemini long-context reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Halo Security MCP to Google ADK

Create your Vinkius account to connect Halo Security 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 Halo Security with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Halo Security Risk Trends Using Google ADK

The `get_security_risk` tool provides immediate access to your historical risk scores, which your Google ADK agent parses alongside BigQuery security logs. This combination allows Gemini to spot long-term exposure trends across millions of tokens of context. Because the ADK handles massive context windows, your agent can cross-reference active vulnerabilities from `list_issues` with your entire cloud deployment history. You get deep, data-driven security audits without hitting context limits.

Run Automated Halo Scans with Gemini and This MCP Server

The `trigger_scan` tool initiates active vulnerability assessments, while `add_target` expands your monitored surface when new Google Cloud projects launch. This MCP server connects your Vertex AI pipelines directly to your external scanner. Your agent monitors infrastructure changes in GCP and immediately registers new endpoints for scanning. This setup ensures that no new service goes unmonitored, closing the gap between deployment and security verification.

Map Halo Open Ports and Technologies on Google Cloud

The `list_technologies` tool identifies outdated libraries, while `list_open_ports` and `list_certificates` find misconfigured network nodes. Your Google ADK agent analyzes these findings to flag potential entry points for attackers. By feeding this structural data directly into Gemini, your agent can generate precise remediation steps. You no longer have to manually correlate open ports with outdated web server software.

Setup guide

Set up Halo Security 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 Halo Security 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="Halo Security_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Halo Security 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 Halo 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 Halo 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 Halo Security MCP in Google ADK

You initialize the connection using `McpToolset` with your Vinkius HTTP endpoint URL. Then, you pass this toolset directly to your `LlmAgent` in your Python environment, exposing the MCP server tools to Gemini.

Yes, the Google ADK allows Gemini to process massive lists of issues returned by `list_issues` or `list_targets`. The model can analyze thousands of targets simultaneously to find patterns in your attack surface.

Your Google ADK agent can query BigQuery for internal asset lists and then run `list_targets` to find gaps between internal records and external reality. This makes it easy to spot shadow IT.

Yes, you can use the optional `tool_names` filter in the ADK `McpToolset` configuration. This allows you to restrict the agent to read-only tools like `list_dns_records` and block active tools like `trigger_scan`.

All SSL/TLS data, DNS records, and vulnerability details are processed within ephemeral V8 sandboxes. Your sensitive network configurations never persist outside of your designated Google Cloud environment and the Halo API.

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