Skip to main content
Glama
Instatus MCP Server

Instatus MCP Server

by OfirOhan

Instatus MCP Server

CI MCP License: MIT

A Model Context Protocol server for Instatus. It lets Claude, Cursor, ChatGPT and other AI agents check what's down, open and update incidents, flip component statuses and schedule maintenance on your status page, straight from the chat or terminal where the on-call engineer is already working.

Unofficial. This is a community project and is not affiliated with Instatus. It was built from Instatus's public API docs.

What you can ask your agent

  • "Is anything on our status page degraded right now? Summarize any open incidents."

  • "Open an incident on the API component: elevated 5xx errors, we're investigating. Don't notify subscribers yet."

  • "Post an update on that incident: root cause identified, a fix is rolling out. Mark the API as degraded instead of partial outage."

  • "We're back. Resolve the incident and set everything to operational."

  • "Schedule a 45-minute database maintenance window for Sunday 02:00 UTC on API and Dashboard."

Related MCP server: GetMonitor MCP Server

Tools

Tool

What it does

Writes?

get_current_user

Who owns this API key

No

list_status_pages

Your pages with id, subdomain and public URL

No

get_status_overview

One-call "is anything down?": overall state, components by status, open incidents with latest update, upcoming maintenance

No

list_components / get_component

Components and their current status

No

list_incidents / get_incident

Incidents with their update timeline, filterable by status

No

list_maintenances

Scheduled, in-progress and past maintenance

No

set_component_status

Change one component's status without an incident

Yes

create_incident

Open an incident and set the impact on affected components

Yes

post_incident_update

Add a public update, optionally changing component impact

Yes

resolve_incident

Post a RESOLVED update and set affected components back to OPERATIONAL in one step

Yes

schedule_maintenance

Announce a maintenance window (auto start/end, components shown as under maintenance)

Yes

delete_incident

Delete an incident

Destructive

Design notes:

  • Subscribers are not notified by default. Every write tool takes notify, which defaults to false, so an agent can't email your customers unless you ask it to.

  • get_status_overview pulls components, unresolved incidents and maintenances in parallel and returns a short summary instead of three raw API dumps.

  • resolve_incident and post_incident_update look up the incident's components for you, so the agent doesn't need to track component IDs between turns.

  • All tools carry MCP annotations (readOnlyHint, destructiveHint), so clients can ask before publishing anything.

Setup

  1. Create an API key in Instatus: User settings → Developer settings.

  2. Build it:

git clone https://github.com/OfirOhan/instatus-mcp.git
cd instatus-mcp && npm install && npm run build

Claude Desktop

Add this to claude_desktop_config.json:

{
  "mcpServers": {
    "instatus": {
      "command": "node",
      "args": ["/absolute/path/to/instatus-mcp/dist/index.js"],
      "env": { "INSTATUS_API_KEY": "your-api-key" }
    }
  }
}

Claude Code / Cursor / other MCP clients

claude mcp add instatus -e INSTATUS_API_KEY=your-api-key -- node /path/to/instatus-mcp/dist/index.js

For Cursor and other clients, use the same command with INSTATUS_API_KEY in the environment.

Variable

Default

Notes

INSTATUS_API_KEY

(required)

Your Instatus API key

INSTATUS_BASE_URL

https://api.instatus.com

Override for testing

Development

npm install
npm test   # builds, runs unit tests and an end-to-end MCP stdio test against a fake Instatus API

The tests run on Node 20, 22 and 24 in CI.

Author

Built by Ofir Ohana, an AI agents engineer. Issues and PRs are welcome.

License

MIT

Available Tools

14 tools
create_incidentOpen an incidentA

Publish a new incident on the public status page. Affected components are set to componentStatus (default PARTIALOUTAGE). Draft the wording with the user before publishing.

Inputs: name (required), pageId (required), message (required), notify, +5 more.

delete_incidentDelete incidentA
Destructive

Permanently delete an incident and its history from the status page. Cannot be undone, so confirm first.

Inputs: pageId (required), incidentId (required).

get_componentGet componentA
Read-only

Get one component with its description, status, group and uptime settings.

Inputs: pageId (required), componentId (required).

get_current_userGet current userA
Read-only

Get the Instatus user that owns the API key (id, name, email).

Inputs: no named parameters.

get_incidentGet incidentA
Read-only

Get one incident with its full update timeline and affected components.

Inputs: pageId (required), incidentId (required).

get_status_overviewStatus overviewA
Read-only

One-call answer to 'is anything down right now?' for a status page: overall state, components grouped by status, open incidents with their latest update, and upcoming or in-progress maintenance.

Inputs: pageId (required).

list_componentsList componentsB
Read-only

List the components (services) shown on a status page with their current status and group.

Inputs: pageId (required), page, per_page.

list_incidentsList incidentsA
Read-only

List incidents on a status page, newest first, with their updates and affected components. Use status to filter, e.g. 'INVESTIGATING,IDENTIFIED,MONITORING' for open incidents.

Inputs: pageId (required), page, status, per_page, +1 more.

list_maintenancesList maintenancesA
Read-only

List scheduled, in-progress and past maintenance windows on a status page.

Inputs: pageId (required), page, per_page.

list_status_pagesList status pagesA
Read-only

List the user's Instatus status pages (id, name, subdomain, custom domain, overall status).

Inputs: page, per_page.

post_incident_updatePost incident updateA

Add a public update to an incident (e.g. move from INVESTIGATING to IDENTIFIED with a new message). If componentStatus is given it is applied to the incident's components.

Inputs: pageId (required), status (required), message (required), incidentId (required), +2 more.

resolve_incidentResolve incidentA

Resolve an incident in one step: posts a RESOLVED update and sets every affected component back to OPERATIONAL.

Inputs: pageId (required), incidentId (required), notify, message.

schedule_maintenanceSchedule maintenanceA

Announce a planned maintenance window. By default it starts and ends automatically, and affected components show UNDERMAINTENANCE while it runs.

Inputs: name (required), start (required), pageId (required), message (required), +6 more.

set_component_statusSet component statusA
Idempotent

Change a component's status on the public status page without opening an incident (e.g. mark the API as DEGRADEDPERFORMANCE, or back to OPERATIONAL). This is visible to customers.

Inputs: pageId (required), status (required), componentId (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 14 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes: user/page/component/incident/maintenance operations are separated by resource and action. The main mild ambiguity is between post_incident_update and resolve_incident, since both can update incident wording/status, but resolve_incident's one-step RESOLVED + component-reset behavior makes it distinguishable.

    Naming Consistency5/5

    All tool names are snake_case and consistently lead with a verb: get_, list_, set_, create_, post_, resolve_, delete_, schedule_. The pattern is predictable across every tool, with no mixing of conventions.

    Tool Count5/5

    14 tools is well-scoped for a status-page operations server. The set covers user context, page viewing, component status, incident lifecycle, and maintenance without obvious bloat.

    Completeness4/5

    Incident lifecycle coverage is strong: list/get/create/update/resolve/delete. Component and maintenance surfaces are thinner (no create/update/delete component, no update/cancel maintenance), but the core public status-page workflows are covered and these gaps are likely administrative or out of scope.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      Enables unified management of maintenance windows and incidents across Atlassian Statuspage and Uptime Kuma. It allows AI assistants to schedule maintenance, update service statuses, and list monitors through a single MCP-compatible interface.
      9
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to check real-time status, uptime, and incidents for 200+ popular APIs (Stripe, OpenAI, AWS, GitHub, Twilio, etc.) through read-only, no-authentication tools.
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to read monitors and incidents and to create, update, and resolve incidents on Kener v4 status pages, with read-only tools marked safe and write operations available when permitted.
      6
      MIT