How to Use the UpGuard MCP in Google ADK

Q: How does UpGuard assess organizational risks with the Google ADK?

The MCP Server provides listaccountrisks, which gives a real-time view of all active vulnerabilities. Your agent ingests this data and can query specific tools like listuserrisks to drill down into problematic areas.

Q: Can I assess vendor risk with UpGuard using the Google ADK?

Absolutely. You list all vendors using listvendors, and then you call listvendorrisks. The agent uses this data to determine if a partner needs immediate review.

Q: What kind of monitoring does UpGuard offer for IPs and domains with the Google ADK?

The tools listmonitoredips and listmonitoreddomains allow your agent to confirm that all critical network assets are under continuous scanning. This confirms a stable perimeter.

Q: Does UpGuard help track identity breaches when using the Google ADK?

Yes. The listidentitybreaches tool provides a direct list of compromised identities, which is critical data that your agent can process alongside user risk data.

Assess your attack surface risk with Google ADK's enterprise capabilities.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect UpGuard MCP to Google ADK

Create your Vinkius account to connect UpGuard 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 UpGuard with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Out All Organizational Risks via MCP Server

The agent starts by calling `list_account_risks` to get a baseline of all active risks across the organization. This comprehensive view is crucial for understanding overall security posture. It can then narrow the focus using `list_user_risks`, allowing your enterprise agents to target risk mitigation efforts against specific users or departments.

Track Vendor and Third-Party Security Posture

Building on external dependencies, you'll use `list_vendors` to gather a complete roster of monitored partners. From that list, calling `get_vendor` lets your agent pull deep details for one vendor at a time. Furthermore, using `list_vendor_risks` provides the actual security status for those vendors, making it easy to identify potential supply chain vulnerabilities.

Verify Domain and Identity Exposure

Your agent can verify your public presence by running `list_monitored_domains` and `list_monitored_ips`. This confirms all assets are accounted for in the monitoring system. For identity management, using `list_identity_breaches` gives a clear record of past compromises. This data is invaluable when feeding into BigQuery for long-term trend analysis.

Setup guide

Set up UpGuard 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 UpGuard 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="UpGuard_agent",
    model="gemini-2.0-flash",
    instruction="You have access to UpGuard 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 UpGuard. 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 UpGuard 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 UpGuard MCP in Google ADK

The MCP Server provides `list_account_risks`, which gives a real-time view of all active vulnerabilities. Your agent ingests this data and can query specific tools like `list_user_risks` to drill down into problematic areas.

Absolutely. You list all vendors using `list_vendors`, and then you call `list_vendor_risks`. The agent uses this data to determine if a partner needs immediate review.

The tools `list_monitored_ips` and `list_monitored_domains` allow your agent to confirm that all critical network assets are under continuous scanning. This confirms a stable perimeter.

Yes. The `list_identity_breaches` tool provides a direct list of compromised identities, which is critical data that your agent can process alongside user risk data.

This server handles records related to identity breaches and user vulnerability scores. Specific data types include those listed in `list_identity_breaches` and individual risk metrics from `list_user_risks`.

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