---
title: "incident-io"
description: "Makes your agent fluent in incident.io: responding to and investigating incidents, working with on-call schedules and escalations, and authoring the operational content, runbooks, skills, and plugins, that incident.io in"
canonical: https://agentpluginsdirectory.com/plugins/incident-io
last-updated: 2026-09-25
---

# incident-io
Makes your agent fluent in incident.io: responding to and investigating incidents, working with on-call schedules and escalations, and authoring the operational content, runbooks, skills, and plugins, that incident.io investigations draw on. Bundles the official incident.io MCP server.
- Slug: incident-io
- Publisher: incident.io
- Repository: https://github.com/incident-io/skills
- Manifest: plugins/incident-io/plugin.json
- Version: 0.20.0
- License: MIT
- Category (editorial): other
- Skills: 5 (architecture, doctor, extensions-review, extensions, skill-authoring)
- MCP servers: 1 (incident_io)
- Stars: 2
- Repository created: 2026-08-21
- Repository last pushed: 2026-09-24
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/incident-io
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What incident-io does, in the publisher's words

Makes your agent fluent in incident.io: responding to and investigating incidents, working with on-call schedules and escalations, and authoring the operational content, runbooks, skills, and plugins, that incident.io investigations draw on.

The plugin bundles the official incident.io MCP server (https://mcp.incident.io/mcp), so installing it connects your agent to your incident.io workspace through a standard OAuth flow the first time a tool is used.

Run these skills on Opus/Sol level or higher. Smaller models follow their workflows unreliably.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/incident-io/skills/HEAD/plugins/incident-io/README.md

## Skills

- architecture: Answer questions about how a team builds, deploys, and runs its software, what a system is, where it runs, what it depends on, and the real names of things (cloud projects, clusters, namespaces, hostnames, buckets), from architecture docs wherever they live. Also guides writing those docs: an inter…
- doctor: Review the health of your incident.io agent estate, plugins, skills, connections, and say what to fix, without fixing anything itself. Use whenever anyone asks whether their incident.io setup is healthy, what's degraded, or what to improve, in any phrasing, one-off or as a recurring review. Every f…
- extensions-review: Review what your extensions did over a period: the skill loads that made a real difference, told through the incident or conversation each one happened in, and the incidents no skill or runbook covered. Use whenever anyone wants a review, digest, or pulse of extension or skill usage over a window,…
- extensions: Understand the extensions so that you can help a user configure and manage their incident.io agent estate. Use whenever you're working with incident.io plugins, skills, connectors or MCPs in any way ("I want to set up an incident plugin"), when someone new wants to give incident.io's agents their o…
- skill-authoring: Create and improve the skills in your own plugins, the ones incident.io's agents and your coding agents load. Use whenever you're writing, editing, or reviewing a skill in any way: creating one, improving one from usage feedback or a review brief, or asking what makes a good skill.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- incident_io: transport: streamable-http; url: https://mcp.incident.io/mcp

Read from the plugin's own mcp.json. Environment variable names only, never values.