How to Use the Fluxguard MCP in Google ADK

Q: How do I register the Fluxguard MCP server in Google ADK?

Use the McpToolset class with StreamableHttpServerParameters pointing to your Vinkius URL. Pass the toolset instance directly into your LlmAgent tool list.

Q: Can I limit which Fluxguard tools the Google ADK agent can access?

Yes. Use the optional toolnames filter when initializing your toolset to expose only specific tools like listalerts or getchange.

Q: Does Fluxguard support Gemini long-context analysis in Google ADK?

Yes. The agent can pull massive change logs using listchanges and feed the entire raw text history directly into Gemini's million-token context window.

Analyze massive web change histories inside Google ADK using Gemini long-context reasoning and this Fluxguard MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fluxguard MCP to Google ADK

Create your Vinkius account to connect Fluxguard 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 Fluxguard with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deep history analysis with Google ADK

The `list_snapshots` tool retrieves historical versions of your monitored pages for deep analysis. With Gemini's huge context window, your agent can process months of visual changes in a single pass to spot slow-burning site drift. Your agent combines this historical data with BigQuery records to correlate site changes with traffic drops. The agent runs these checks automatically, outputting clean reports directly to your team.

Targeted enterprise monitoring using MCP Server filters

The `list_sites` tool returns your entire monitored inventory to help the agent map out your attack surface. If you want to limit what the agent can touch, the Google ADK lets you restrict tools using a name filter. For active investigations, the agent calls `get_site` to pull granular details on a specific asset. This targeted approach prevents your enterprise agent from wasting API quota on clean domains.

Automated crawling and alert dispatching

The `initiate_crawl` tool forces an on-demand scan of critical endpoints when your cloud logging detects suspicious activity. The agent handles the execution, bypassing slow cron jobs. If the crawl detects a change, the agent pulls the details with `get_change` and alerts your team. The agent then runs `acknowledge_alert` once a human confirms the change is safe.

Setup guide

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

Use the `McpToolset` class with `StreamableHttpServerParameters` pointing to your Vinkius URL. Pass the toolset instance directly into your `LlmAgent` tool list.

Yes. Use the optional `tool_names` filter when initializing your toolset to expose only specific tools like `list_alerts` or `get_change`.

Yes. The agent can pull massive change logs using `list_changes` and feed the entire raw text history directly into Gemini's million-token context window.

Write a simple Python script where your agent monitors BigQuery for anomalies, then calls `initiate_crawl` to verify the live site state immediately.

Raw HTML and visual snapshots stay within Fluxguard and Vinkius's secure sandbox. The MCP Server only transmits the specific change diffs requested by your agent, keeping your target page source code 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