How to Use the HackEDU (Security Journey) MCP in Google ADK

Q: How do I restrict which HackEDU (Security Journey) tools are exposed to Google ADK?

You can use the optional toolnames filter when initializing your MCP toolset. This lets you limit the agent to read-only tools like getteamprogress and listcontent, preventing it from executing write actions like createissue in production.

Q: How is my HackEDU (Security Journey) user and progress data secured within Google ADK?

All API requests to retrieve user details via getuser or team lists via listteams run inside a zero-trust V8 MCP sandbox. Vinkius manages the authentication tokens securely, meaning your raw HackEDU credentials are never exposed to the LLM or stored in cloud logs.

Run enterprise-grade security training automation on Google Cloud using Google ADK and Gemini models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HackEDU (Security Journey) MCP to Google ADK

Create your Vinkius account to connect HackEDU (Security Journey) 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 HackEDU (Security Journey) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect vulnerability data using Google ADK

Combine your security findings with Gemini's long-context capabilities to analyze team performance. The ADK allows your agent to pull historical security data from BigQuery, then call `list_vulnerabilities` to map those issues to specific CWE targets. This lets you align real-world production errors with training needs. The agent checks the available modules using `list_content` to find corresponding interactive exercises. Because Gemini handles massive token contexts, your agent can evaluate entire training catalogs in a single step to build personalized learning paths.

Trigger adaptive training plans via MCP

Automate how you assign security training when new bugs emerge. Your agent uses `list_issues` to find active vulnerabilities synced from external platforms. It then calls `create_issue` to push those findings into HackEDU, which triggers targeted training plans for the responsible developers. You can track whether these assignments are actually working by calling `list_adaptive_training_plans`. This MCP Server integration ensures that training is never a generic annual exercise, but a direct response to actual code defects.

Track organization-wide training progress

Manage large engineering organizations without manual oversight. Your agent queries `list_teams` to understand your organizational structure, then runs `get_team_progress` to identify gaps. This allows your security team to see which departments are completing their modules. For deeper detail, the agent calls `get_user_progress` to inspect individual completion rates. This direct tracking helps you report compliance metrics to leadership directly from your Google Cloud console.

Setup guide

Set up HackEDU (Security Journey) 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 HackEDU (Security Journey) 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="HackEDU (Security Journey)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to HackEDU (Security Journey) 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 HackEDU. 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 HackEDU (Security Journey) 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 HackEDU (Security Journey) MCP in Google ADK

You can use the optional `tool_names` filter when initializing your MCP toolset. This lets you limit the agent to read-only tools like `get_team_progress` and `list_content`, preventing it from executing write actions like `create_issue` in production.

Yes. You can connect to the Vinkius managed endpoint using the `StreamableHttpServerParameters` class. This allows your Gemini models to interact with the HackEDU API over a secure, cloud-hosted HTTP MCP transport.

Absolutely. Your agent can query vulnerability trends from your BigQuery database, then use `list_vulnerabilities` to find matching training content. This makes it easy to build automated workflows that respond directly to your internal cloud security logs.

Gemini can hold over a million tokens of context. This allows your agent to ingest the entire output of `list_content` alongside thousands of user records from `list_users` to build highly customized training schedules without hitting token limits.

All API requests to retrieve user details via `get_user` or team lists via `list_teams` run inside a zero-trust V8 MCP sandbox. Vinkius manages the authentication tokens securely, meaning your raw HackEDU credentials are never exposed to the LLM or stored in cloud logs.

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