How to Use the Incident.io MCP in LangChain

Q: How do I connect LangChain to the Incident.io MCP Server?

Install the langchain-mcp-adapters package and initialize the MultiServerMCPClient with your Vinkius endpoint. Retrieve the tools using client.gettools() and pass them directly to your agent. This lets your agent call endpoints like listincidents during a run.

Q: Can a LangChain agent assign incident roles using Incident.io?

Yes, the agent uses listincidentroles to find valid roles and maps them to active users. It chains this with listusers to verify the assignment. You configure this behavior within a standard LangGraph state machine.

Build LangChain agents that pull Incident.io rosters, query active alerts, and assign handlers during outages.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain incident lookups with LangChain agents

This Incident.io MCP Server links live operational data directly into your LangChain reasoning loops. Your agent starts by calling `list_incidents` to find active outages, then immediately feeds those IDs into `get_incident` to extract the technical context. By passing outputs directly between steps, you eliminate manual data entry. You get full visibility into this execution chain through LangSmith tracing. Every tool execution, from querying `list_users` to identifying the active responder, is logged with exact latency and token usage. This lets you debug complex multi-step triage pipelines without guessing where a model stalled.

Automate on-call routing via LangChain chains

This MCP Server exposes your active rosters so LangChain agents can route alerts without human intervention. The agent queries `list_schedules` to see who is currently on the hook, then cross-references those IDs with `list_users` to get their contact details. No more hunting through spreadsheets while production is burning. The model evaluates the severity of the issue using `list_severities` before making routing decisions. High-priority incidents go to the primary on-call engineer, while minor blips are logged quietly. You build a self-contained triage chain that respects your team's sleep schedules.

Classify alerts using LangChain and Incident.io

This MCP Server allows your LangChain agent to inspect your workspace schema using `list_custom_fields` and `list_incident_types`. The agent reads incoming alert payloads, determines the incident type, and maps the data to your specific organizational structure. By combining these classification tools with `list_incident_roles`, your pipeline automatically assigns the correct commander and communications lead. You run these steps sequentially, ensuring every new incident has the right metadata attached from the start.

Setup guide

Set up Incident.io MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Incident.io tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "incidentio-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Incident.io transactions"
    })
    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 LangChain

Install the `langchain-mcp-adapters` package and initialize the `MultiServerMCPClient` with your Vinkius endpoint. Retrieve the tools using `client.get_tools()` and pass them directly to your agent. This lets your agent call endpoints like `list_incidents` during a run.

Yes, the agent uses `list_incident_roles` to find valid roles and maps them to active users. It chains this with `list_users` to verify the assignment. You configure this behavior within a standard LangGraph state machine.

LangSmith captures every tool call automatically, showing you the exact inputs and outputs of tools like `list_schedules`. You see the raw JSON payload returned from the API inside your tracing dashboard. This makes it easy to audit why an agent chose a specific on-call engineer.

You should implement rate-limiting middleware or configure retry logic in your LangChain runnable. The server queries live endpoints like `list_teams`, so high-frequency loops can trigger API limits. Caching static data like catalog types also prevents unnecessary calls.

Your incident details and user directories never persist on the Vinkius platform. The server runs inside an ephemeral V8 Isolate sandbox, executing calls to `get_incident` and immediately discarding the payload. All traffic is encrypted in transit directly to the API.

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