How to Use the FireHydrant MCP in Google ADK

Q: How do I initialize the FireHydrant toolset in Google ADK?

Install the package and use McpToolset with your HTTP server parameters. Pass this toolset directly into your LlmAgent instance to expose the MCP endpoints.

Q: Can I restrict Google ADK to only read FireHydrant data?

Yes. Use the optional toolnames filter when defining your toolset to restrict access. You can expose read-only tools like listincidents and block write operations like updateincident.

Manage your FireHydrant incident lifecycle directly from Google ADK while keeping your Gemini models grounded in real system data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FireHydrant MCP to Google ADK

Create your Vinkius account to connect FireHydrant 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 FireHydrant with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground Gemini reasoning in actual service topology

The `get_service` tool fetches real-time metadata from your service catalog to ground Gemini's recommendations during an active outage. By feeding this data into Google ADK, your agent cross-references broken systems with BigQuery logs to find the root cause. Because Gemini models support massive context windows, your agent can process all output from `list_services` simultaneously. It maps out dependencies across your entire infrastructure without hitting token limits.

Trigger FireHydrant runbooks through Google ADK

The `list_runbooks` tool exposes your documented incident response procedures directly to the Gemini agent. It reads these steps, checks active incident details via `get_incident`, and suggests the next logical mitigation step. This MCP Server integration allows you to run automated incident triage. The agent uses the information to alert the correct on-call rotation over the MCP link.

Coordinate response teams during active outages

The `get_team` tool retrieves on-call responder details so your agent can route alerts to the correct engineering group. It matches failing services to team IDs, ensuring that critical notifications go only to the people who own the code. The agent updates the incident timeline using `add_incident_note` as responders join the bridge. This keeps everyone aligned without forcing engineers to manually type updates while they are actively debugging.

Setup guide

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

Install the package and use `McpToolset` with your HTTP server parameters. Pass this toolset directly into your `LlmAgent` instance to expose the MCP endpoints.

Yes. Use the optional `tool_names` filter when defining your toolset to restrict access. You can expose read-only tools like `list_incidents` and block write operations like `update_incident`.

The agent reads incident logs and service metadata using secure HTTP transport. Vinkius manages the authentication token, so your Google Cloud environment never exposes raw API credentials.

Yes. You can run the server locally over Stdio during development, then switch to Vinkius-hosted HTTP endpoints when deploying your agent to production on Google Cloud.

Your team rosters, on-call schedules, and service catalog details stay strictly within the ephemeral sandbox. Vinkius handles the connection over a zero-trust network, meaning no data is stored or logged outside your session.

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