How to Use the Incident.io MCP in AutoGen

Q: How do I register the Incident.io MCP Server with AutoGen?

Use the mcpservertools helper from the autogen-ext package to load the tools. Pass the resulting tool list to your AssistantAgent constructor. This grants your conversational agents direct access to endpoints like listincidents.

Q: How do AutoGen agents handle Incident.io on-call schedules?

The agents query listschedules to find active responders and listteams to identify their department. If a handoff is needed, the conversation loop coordinates the transition. This automates the escalation path during complex outages.

Q: Does AutoGen support the HTTP transport for this MCP Server?

Yes, you connect using the StreamableHttpServerParams pointing to your Vinkius endpoint. This handles the secure connection and lets your agents invoke tools like getincident over standard HTTP.

Q: What happens to my Incident.io custom fields data in AutoGen?

All queries to listcustomfields run through a secure, single-use V8 Isolate container. Vinkius does not store or log the payloads returned by the Incident.io API. Your workspace metadata is kept strictly private and is only visible to your active agent session.

Deploy AutoGen agents that debate incident severity, verify on-call rosters, and coordinate outages using Incident.io.

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 AutoGen

Create your Vinkius account to connect Incident.io to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Incident.io triage with AutoGen agents

This Incident.io MCP Server allows multiple AutoGen agents to collaborate on active outages. A triage agent pulls raw alert data using `list_incidents`, while a coordinator agent queries `list_severities` to propose an incident level. They debate the classification in a structured conversation before making a final decision. This multi-perspective check ensures you don't wake up the wrong engineering team for a minor warning.

Resolve on-call handoffs using AutoGen and MCP Server

This Incident.io MCP Server exposes your team directory so AutoGen agents can manage responder transitions. One agent checks the active schedule via `list_schedules`, while another verifies responder availability using `list_users`. If the primary responder is unresponsive, the agents negotiate an escalation path. They query `list_teams` to find backup coverage and assign the incident to the next qualified engineer.

Assign incident roles via AutoGen conversations

This MCP Server provides the tools needed to structure your response team during a crisis. Your AutoGen agents query `list_incident_roles` and `list_incident_types` to determine who should lead the response. The agents assign specific roles based on the incident type and log the decisions via `get_incident`. This collaborative automation keeps your response organized without requiring manual coordination from the engineering lead.

Setup guide

Set up Incident.io MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Incident.io tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Incident.io_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Incident.io data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Incident.io_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Incident.io data")
    print(result.messages[-1].content)

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 AutoGen

Use the `mcp_server_tools` helper from the `autogen-ext` package to load the tools. Pass the resulting tool list to your `AssistantAgent` constructor. This grants your conversational agents direct access to endpoints like `list_incidents`.

Yes, you can set up one agent to analyze logs and another to query `list_severities`. They discuss the impact of the outage and reach a consensus on the correct severity. Once agreed, they update the incident record.

The agents query `list_schedules` to find active responders and `list_teams` to identify their department. If a handoff is needed, the conversation loop coordinates the transition. This automates the escalation path during complex outages.

Yes, you connect using the `StreamableHttpServerParams` pointing to your Vinkius endpoint. This handles the secure connection and lets your agents invoke tools like `get_incident` over standard HTTP.

All queries to `list_custom_fields` run through a secure, single-use V8 Isolate container. Vinkius does not store or log the payloads returned by the Incident.io API. Your workspace metadata is kept strictly private and is only visible to your active agent 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