incident.io MCP Server
Connect incident.io to your AI agents with the incident.io MCP server.
Updated
What is incident.io MCP?
The incident.io MCP server is a Model Context Protocol server that connects incident.io to AI agents and assistants as a set of tools. With it connected, an agent can work with incident.io (incident management — on-call, alerts, response, and post-incident reviews) directly — instead of you copying data in and out by hand.
It is a remote MCP server that uses OAuth, so you point your client at the server URL, authorize once, and the incident.io tools become available to the model.
Connect the incident.io MCP server
Connect incident.io MCP to Claude Code
- 1
Add the server
Use `claude mcp add` with the incident.io MCP server URL (or its `npx` command), following the official docs.
- 2
Authorize
Complete authentication (OAuth) so Claude Code can call the server.
- 3
Verify
Ask Claude to use a incident.io tool to confirm the connection is live.
Connect incident.io MCP to Cursor
- 1
Open MCP settings
In Cursor, go to Settings → MCP → Add new server.
- 2
Add incident.io
Provide the incident.io MCP server URL or command and complete authentication.
- 3
Test
Reference incident.io from chat to confirm Cursor can reach the tools.
Sample use cases
An on-call engineer asks the agent for a summary of all active incidents
It lists open incidents by severity, current status, assigned responders, and time since creation.
After an incident is resolved, an agent pulls the full timeline — actions taken, status changes, and messages
It drafts a post-incident review document with a chronological timeline, root cause section, and action items.
A team lead asks who is on-call for the payments service this week
The agent returns the current on-call schedule with primary and secondary responders and their shift times.
An agent monitors incident response times across teams over the past month
It calculates MTTA (mean time to acknowledge) and MTTR (mean time to resolve) by team, highlighting outliers.
During an active incident, an agent creates a status update visible on the public status page
It posts a clear customer-facing update with the affected component, current status, and estimated resolution time.
An agent reviews all incidents from the past quarter tagged with a specific service
It identifies recurring failure patterns and suggests reliability improvements based on incident frequency and cause.
An agent tracks escalation paths during an active P1 incident
It monitors whether the right people have been paged, how quickly they acknowledged, and flags stalled escalations.
Using incident.io MCP with Gamut
On Gamut, the incident.io MCP server becomes a tool your agents use inside an automated, event-driven workflow — triggered by an event or a schedule, acting through incident.io and your other connected MCP servers, with the connection managed by Gamut rather than a local config file.
Frequently asked questions
What is the incident.io MCP server?
It is a Model Context Protocol server that exposes incident.io to AI agents as tools so they can work with it (incident management — on-call, alerts, response, and post-incident reviews).
How do I connect the incident.io MCP server?
Point your MCP client (Claude, Cursor, or Gamut) at the incident.io MCP server URL and complete authentication (OAuth). See the official documentation for the exact URL and scopes.
Can I use incident.io MCP with Gamut?
Yes — Gamut supports the incident.io MCP server, so your agents can use it as a tool in automated, triggered workflows.
Is the incident.io MCP server free?
The MCP server itself is open-source, but you need an incident.io account to connect it. incident.io offers free and paid tiers depending on your team size and feature needs.
Is the incident.io MCP server hosted or self-hosted?
It runs locally alongside your AI tool (e.g., Claude Code or Cursor) and connects to the incident.io cloud API. You self-host the MCP server; incident.io hosts the data.
Can the incident.io MCP server manage incident status and updates?
Yes. It supports reading incident data, posting status updates, and tracking response timelines — covering the core incident management workflow.
Does it support on-call schedule lookups?
Yes. You can query on-call schedules to see who is currently responsible for a given service, including primary and secondary responders.