Instatus MCP Server
Provides tools for interacting with the Instatus status page API, enabling AI agents to check service health and manage status pages programmatically: get the current user, list status pages, get a one-call overview of overall state, components, open incidents and upcoming maintenance, list and get components, incidents and maintenances, and perform write operations such as setting component statuses, creating incidents, posting incident updates, resolving incidents (restoring affected components to operational), scheduling maintenance windows, and deleting incidents.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Instatus MCP Server Is anything on our status page degraded right now?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Instatus MCP Server
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? |
| Who owns this API key | No |
| Your pages with id, subdomain and public URL | No |
| One-call "is anything down?": overall state, components by status, open incidents with latest update, upcoming maintenance | No |
| Components and their current status | No |
| Incidents with their update timeline, filterable by status | No |
| Scheduled, in-progress and past maintenance | No |
| Change one component's status without an incident | Yes |
| Open an incident and set the impact on affected components | Yes |
| Add a public update, optionally changing component impact | Yes |
| Post a RESOLVED update and set affected components back to OPERATIONAL in one step | Yes |
| Announce a maintenance window (auto start/end, components shown as under maintenance) | Yes |
| Delete an incident | Destructive |
Design notes:
Subscribers are not notified by default. Every write tool takes
notify, which defaults tofalse, so an agent can't email your customers unless you ask it to.get_status_overviewpulls components, unresolved incidents and maintenances in parallel and returns a short summary instead of three raw API dumps.resolve_incidentandpost_incident_updatelook 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
Create an API key in Instatus: User settings → Developer settings.
Build it:
git clone https://github.com/OfirOhan/instatus-mcp.git
cd instatus-mcp && npm install && npm run buildClaude 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.jsFor Cursor and other clients, use the same command with INSTATUS_API_KEY in the environment.
Variable | Default | Notes |
| (required) | Your Instatus API key |
|
| Override for testing |
Development
npm install
npm test # builds, runs unit tests and an end-to-end MCP stdio test against a fake Instatus APIThe 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 toolscreate_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 incidentADestructive
Permanently delete an incident and its history from the status page. Cannot be undone, so confirm first.
Inputs: pageId (required), incidentId (required).
get_componentGet componentARead-only
Get one component with its description, status, group and uptime settings.
Inputs: pageId (required), componentId (required).
get_current_userGet current userARead-only
Get the Instatus user that owns the API key (id, name, email).
Inputs: no named parameters.
get_incidentGet incidentARead-only
Get one incident with its full update timeline and affected components.
Inputs: pageId (required), incidentId (required).
get_status_overviewStatus overviewARead-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 componentsBRead-only
List the components (services) shown on a status page with their current status and group.
Inputs: pageId (required), page, per_page.
list_incidentsList incidentsARead-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 maintenancesARead-only
List scheduled, in-progress and past maintenance windows on a status page.
Inputs: pageId (required), page, per_page.
list_status_pagesList status pagesARead-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 statusAIdempotent
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
Scored across 14 tools
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.
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.
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.
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
Read pages, components, incidents and maintenances; create and update incidents in Statuspage.
Read status-page status, services, incidents and metrics; create, update and publish incidents.
Status pages and uptime monitoring: read status, monitors and incidents; open incidents.
Read Status.io components, incidents, maintenance; post incidents, schedule maintenance, set status.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables 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.9MIT

GetMonitor MCP Serverofficial
AlicenseCqualityCmaintenanceConnects AI assistants to GetMonitor status pages, monitors, incidents, and maintenance schedules via read-only tools.10015 npmApache 2.0- AlicenseNot gradedqualityCmaintenanceEnables 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
- AlicenseAqualityBmaintenanceEnables 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.6MIT