Instatus MCP for AI. Manage system health and outages via natural language.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
How this MCP server connects to your AI agent
Instatus (Status Pages API) connects your AI agent directly to your service health data. You can manage incidents, update component statuses, and pull system metrics without leaving your IDE or terminal.
Keep users informed in real-time during an outage.
What AI agents can do with Instatus (Status Pages API) Automation
Add metric datapoint
Adds one single data point to an existing tracked metric.
Add metric datapoints bulk
Adds multiple performance datapoints to a metric at once.
Add metric
Adds a brand new performance metric to your status page record.
Create new incidents or modify existing ones to keep stakeholders informed during unplanned downtime.
Change the status of specific infrastructure parts, like APIs or databases, from 'Operational' to 'Degraded'.
List all active incidents and maintenance windows for a complete view of service availability.
Add, update, or delete metrics data points to track performance over time.
Ask an AI about this
Waiting for input…
What AI agents can do with Instatus (Status Pages API) - 28 Tools
Use these tools to interact with every aspect of your status page, from managing metrics data points to creating and updating full incident reports.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Instatus (Status Pages API) on VinkiusAdd Metric Datapoint
Adds one single data point to an existing tracked metric.
Add Metric Datapoints Bulk
Adds multiple performance datapoints to a metric at once.
Add Metric
Adds a brand new performance metric to your status page record.
Add Subscriber
Registers one new person who needs status page updates.
Add Subscribers Bulk
Bulk adds up to 100 subscribers to your service pages.
Add Teammate
Adds a new team member to the status page user list.
Create Component
Creates an entirely new infrastructure component entry on your status page.
Create Incident From Template
Creates an incident using pre-written templates to save time during reporting.
Create Incident
Generates a fresh incident report for the service, noting the outage details.
Create Maintenance
Sets up a planned maintenance window on the status page for future reference.
Delete Component
Removes an unnecessary component from your active service listing.
Delete Incident
Clears out old or resolved incident reports from the page history.
Delete Maintenance
Removes a planned maintenance window that has already passed.
Delete Metric Datapoints
Delete datapoints from a metric
Get Component
Retrieves all current details for a specific component on the page.
Get Incident
Fetches all information about one specific incident report.
Get Maintenance
Gets details and dates for a particular maintenance window.
List Components
Pulls a list of every component currently listed on the status page.
List Incidents
Gets a full rundown of all past and present incidents for the site.
List Maintenances
Lists every planned maintenance event recorded on the page.
List Metrics
Retrieves a list of all tracked performance metrics for the service.
List Subscribers
Gets a roster and details of every person subscribed to status updates.
List Teammates
Retrieves the full list of team members associated with the service page.
Remove Subscriber
Unsubscribes a specific user from receiving status updates.
Remove Teammate
Removes a team member's account access to the page.
Update Component
Changes the status or details of an already listed component.
Update Incident
Modifies details, like severity or resolution time, for an existing incident report.
Update Maintenance
Adjusts the dates or status of a scheduled maintenance window.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Instatus integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Instatus (Status Pages API), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Built on the Model Context Protocol (MCP) for Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 28 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Tracking system uptime used to mean clicking through five different dashboards., Solved with Vinkius AI Gateway
Today, if the API fails, you have to switch between your main dashboard, the incidents tab, and then find a separate component tracker. You copy the error code from one place, paste it into another, and manually change status flags across three different views just to tell people what's going on.
With this MCP, that process collapses into a single conversation with your agent. Tell it: 'The database is down.' Your agent handles calling `update_component` for the database, and then automatically calls `create_incident` so the whole team knows about the outage right away.
Instatus MCP gives you immediate control over your status pages.
You no longer need to manually update every component when a fix rolls out. You simply tell your agent, and it executes `update_component` for the specific part that's back online. Same thing for maintenance windows; instead of updating tickets, you call `update_maintenance`.
The difference is simple: Instead of managing status pages with manual clicks and copy-paste errors, you manage them through code and conversation.
What your AI can actually do with this
When things break, you don't have time for dashboards. This MCP lets you manage all status page content—incidents, components, and metrics—using natural conversation through any AI client. Instead of jumping between multiple systems to figure out the status, your agent handles it all. It’s about making sure the right people get accurate updates instantly.
For instance, if a database component goes down, you can tell your agent to update its status and simultaneously create an incident report for the team. The system records everything automatically. Because this MCP is hosted on Vinkius, you access all these powerful tools in one place. It’s pure command-line reliability for service monitoring.
019e5d26-f0c7-7324-8045-200ba917efa2 
Here's how it actually works
The bottom line is, you talk to your agent like you're talking to a teammate; it handles the complex API calls behind the scenes.
Subscribe to this MCP and provide your Instatus API Key.
Connect the key to your preferred AI client (e.g., Cursor or Claude).
Tell your agent what you need done: 'Update the database component status to degraded and list all active incidents.'
Who is this actually for?
DevOps engineers who get burned out from clicking through five different dashboards at 2 AM. SREs managing critical, real-time outages. Support staff needing instant system status checks to talk to customers.
Needs to update component statuses and create incident reports manually during a high-stress outage without leaving their terminal.
Uses the MCP to list all active incidents or check historical metrics before deploying a fix, ensuring they don't break anything else.
Checks current system health and incident history via the agent to give customers accurate, consolidated status updates immediately.
What Changes When You Connect
Stop manually updating statuses. Use the agent to update component status, like calling update_component, instantly when an API fails.
Keep a clear audit trail of everything that happened. You can call list_incidents or get_incident to pull up the full history for post-mortem reports.
Handle multiple users easily. Use add_subscribers_bulk and add_teammate to manage who sees what, all from the agent's command line interface.
Track performance data automatically. Instead of spreadsheets, use add_metric_datapoints_bulk to feed metrics directly into your status page for better context.
Coordinate planning with precision. Use the system to set up future work using create_maintenance, keeping outages and planned downtime separate.
See it in action
The immediate outage report
A critical API goes down at 3 AM. Instead of jumping into the status page UI, you tell your agent: 'Create an incident' and then 'Update the API component to degraded.' The agent executes both actions immediately.
The post-mortem review
After a week of downtime, management needs a full report. You ask your agent to run list_incidents and then pull metrics using get_incident for the period in question, giving them one clean data package.
The scheduled change
You're preparing a deployment that requires downtime. You tell your agent to first 'Create maintenance' and then list all components so you can confirm which ones need special attention during the window.
The honest tradeoffs
Manual status checks
A developer opens three tabs—the component page, the incident timeline, and the metrics dashboard—to check if everything is fine.
Don't click around. Ask your agent to run list_components followed by list_incidents. It gives you a consolidated view immediately.
Missing history
Only checking the 'current' status page and missing historical downtime details.
Always check the full history. Use list_incidents to get all past reports, or use get_incident for a specific date range.
Incomplete data entry
Updating only the component name but forgetting to change its status to 'operational' after fixing it.
Always follow up changes. After making a fix, explicitly run update_component and set the status to 'Operational'.
When It Fits, When It Doesn't
Use this MCP if your primary workflow involves real-time, conversational management of service health data—specifically creating incidents or updating component statuses immediately after an alert. It's built for the moment things go wrong. Don't use it if you just need to list a single user or check one specific metric value; that might be overkill. If you only need to fetch static details about a page, a simple read-only API call is fine. But when you need your agent to act—to generate an incident or change a component's status—this MCP is what you want.
Questions you might have
How do I start an incident using the create_incident tool? +
You tell your agent to 'create a new incident.' It will prompt you for details like severity, title, and affected components. This saves you from having to manually fill out all the forms in the web UI.
What is the difference between list_components and get_component? +
list_components gives you a full roster of every component on the page, while get_component dives deep to show all the details for just one specific component.
Can I bulk add metrics using add_metric_datapoints_bulk? +
Yes. This tool lets you send a bunch of metric readings at once, which is way faster than calling add_metric_datapoint for every single data point.
Do I need to update the maintenance window after it's done? +
Yes. After the work is complete, use the agent to call update_maintenance and change its status to 'Completed.' This keeps your record clean for future reference.
What if I want to see all historical issues? Should I use list_incidents? +
Exactly. Using list_incidents gives you the complete history of every reported outage, which is critical for compliance and post-mortem analysis.
What is the best way to manage user accounts using the add_subscriber tool? +
You use this tool to onboard new client access. When adding a subscriber, always confirm their unique identifier and required scope permissions before invoking it. This prevents unauthorized data read/write actions later on.
If I try to update component status with update_component but get an error, how do I troubleshoot? +
First, run the get_component tool using the specific ID you intend to modify. This confirms the resource exists and verifies your access permissions before attempting the update call again.
When should I use add_metric_datapoint instead of adding metrics in bulk? +
Use this single-point tool when you need immediate, isolated data entry. It's ideal for real-time system checks or debugging where only one metric point needs to be logged right now.
Can I update the status of a specific component like 'API' or 'Database'? +
Yes! Use the update_component tool by providing the Page ID and Component ID. You can set the status to 'OPERATIONAL', 'PARTIAL_OUTAGE', 'MAJOR_OUTAGE', or 'UNDER_MAINTENANCE' instantly.
How do I list all current incidents for a specific status page? +
Simply ask the agent to run the list_incidents action for your target Page ID. It will return a list of all recorded incidents, including their current status and history.
Is it possible to create a new incident report through the AI? +
Absolutely. Use the add_incident tool. You can provide a name, message, and status, and the AI will publish the incident to your Instatus page immediately.
We've already built the connector for Instatus. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 28 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.