How to Use the Incident.io MCP in Google ADK

Q: How do I configure the Incident.io MCP Server inside Google ADK?

You initialize the connection using McpToolset with your unique HTTP endpoint URL in your Python environment. Then, you pass this toolset to your Google ADK LlmAgent constructor. The agent automatically discovers all ten tools, including listincidents and listschedules, with zero manual mapping.

Q: Can I limit Google ADK to only query specific Incident.io tools?

Yes, you can use the toolnames filter parameter in the Google ADK toolset configuration to restrict exposure. For example, you can limit your agent to only access listteams and listusers while blocking access to sensitive incident details. This keeps your agent focused and secure.

Q: How does Google ADK use Incident.io data alongside BigQuery?

Your Google ADK agent can query listincidents to get active outage details and then use standard Google Cloud SDKs to write that data to BigQuery. This allows you to build automated reporting pipelines that combine real-time incident data with historical infrastructure metrics.

Connect Incident.io to your Google ADK agents to process massive outage histories alongside your enterprise BigQuery data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Incident.io MCP to Google ADK

Create your Vinkius account to connect Incident.io 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 Incident.io with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze long-context outages with Google ADK

This MCP Server exposes `list_incidents` and `list_custom_fields` to feed your Gemini-powered Google ADK agents with thousands of historical incident records. Because the Gemini models handle massive token windows, your agent can read entire incident histories to detect systemic infrastructure issues. You can pass these tools directly into your `LlmAgent` using `McpToolset`. The agent queries `list_incidents` to pull raw text logs and custom metadata, then uses Google ADK to cross-reference that data with historical post-mortems stored in Google Cloud.

Route alerts to teams using Google ADK

The `list_teams` and `list_incident_roles` tools allow your Google ADK agent to map active incidents to the correct engineering groups in your organization. This automates the initial triage phase by identifying which team owns the affected service. The agent queries `list_teams` to get the team IDs and matches them against the roles returned by `list_incident_roles`. Using Google ADK, you can write a simple Python script that takes this output and triggers notifications across your internal Google Cloud communication channels.

Classify incidents by severity with Google ADK

This MCP Server uses `list_severities` and `list_incident_types` to let your Google ADK agent categorize incoming system alerts. The agent evaluates the severity levels defined in your account to determine how quickly a responder needs to be paged. By integrating these tools with Google ADK, your agent can automatically update BigQuery tables with the current incident types. This gives your engineering leadership real-time dashboards of active outages categorized by the exact severities returned from `list_severities`.

Setup guide

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

You initialize the connection using `McpToolset` with your unique HTTP endpoint URL in your Python environment. Then, you pass this toolset to your Google ADK `LlmAgent` constructor. The agent automatically discovers all ten tools, including `list_incidents` and `list_schedules`, with zero manual mapping.

Yes, you can use the `tool_names` filter parameter in the Google ADK toolset configuration to restrict exposure. For example, you can limit your agent to only access `list_teams` and `list_users` while blocking access to sensitive incident details. This keeps your agent focused and secure.

Your Google ADK agent can query `list_incidents` to get active outage details and then use standard Google Cloud SDKs to write that data to BigQuery. This allows you to build automated reporting pipelines that combine real-time incident data with historical infrastructure metrics.

Google ADK supports both transports, but we host this MCP Server as a managed HTTP service for easy integration. You simply pass the streamable HTTP parameters to your toolset, and we handle the connection, authentication, and execution of tools like `get_incident`.

The server accesses user directories and on-call schedules via `list_users` and `list_schedules` to handle routing. This data is processed in memory inside our ephemeral V8 sandbox and is never stored. All communication between Google ADK and the API is encrypted in transit.

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