Incident.io MCP. Automate incident triage and coordination.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Incident.io MCP Server manages the entire incident response lifecycle. Your AI agent can list all ongoing incidents, check on-call schedules, track custom fields, and manage incident roles.
It gives you a single point of access to critical SRE data, letting you automate triage and coordination without jumping through multiple dashboards.
This is for systems that need fast, reliable incident state retrieval.
What your AI agents can do
Get incident
Retrieves full details for one specific incident ID.
List catalog types
Lists all defined catalog types used in the system.
List custom fields
Lists all custom fields you can track on an incident record.
Your agent retrieves all current information and history for a specific incident ID.
Your agent fetches a list of all recorded incidents, allowing you to check status or find a specific ID.
Your agent pulls all active on-call schedules for any given time frame.
Your agent checks defined roles, teams, and user assignments relevant to incident management.
Your agent lists the predefined categories for incidents and their severity levels.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
019d75b8get incident
Retrieves full details for one specific incident ID.
019d75b8list catalog types
Lists all defined catalog types used in the system.
019d75b8list custom fields
Lists all custom fields you can track on an incident record.
019d75b8list incident roles
Lists every defined role used for incident management.
019d75b8list incident types
Lists all predefined types of incidents.
019d75b8list incidents
Lists a summary of all recorded incidents.
019d75b8list schedules
Lists all current on-call schedules and rotations.
019d75b8list severities
Lists all possible severity levels (e.g., Critical, Major).
019d75b8list teams
Lists all defined teams within the organization.
019d75b8list users
Lists all user accounts available in the system.
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 Incident.io, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ 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
What you can do with this MCP connector
Yo, this MCP server hooks your AI agent straight into Incident.io. It gives you the whole kit and caboodle to run incident response—no more jumping through a million dashboards. Your agent can pull all the critical SRE data you need, automating triage and coordination right from a single chat. It's built for ops teams who need to move fast and know exactly what's going on.
If you need the full story on a specific event, your agent uses get_incident to grab all the current info and history for a specific incident ID. To see what's going down overall, it runs list_incidents, giving you a summary of every recorded incident. You can also check the on-call rotations with list_schedules, pulling all active schedules for any time frame.
For the personnel side of things, your agent checks out the team structure using list_teams and list_users, plus it uses list_incident_roles to check defined roles and user assignments. It also lets you see all the predefined categories for incidents with list_incident_types, and it knows all the possible severity levels with list_severities.
Need to track some weird custom metric? list_custom_fields shows you every custom field you can put on an incident record. Lastly, list_catalog_types shows you every catalog type used in the system.
How Incident.io MCP Works
- 1 Start by telling your agent what you need: 'Show me all high-severity incidents for the database team.'
- 2 The agent executes several tools—maybe
list_incidentsfirst, then filters that list usinglist_teamsand checks the severity usinglist_severities. - 3 You get a consolidated, structured output containing the list of incidents, who is involved, and their current status.
The bottom line is, your agent handles the multi-step API calls you'd normally write, giving you the final answer without you seeing the intermediate steps.
Who Is Incident.io MCP For?
The Site Reliability Engineer (SRE) who gets burned out checking dashboards at 2 AM. The Incident Manager who needs to quickly confirm who owns what during a crisis. Ops engineers who need to automate the initial triage process. If your job involves coordinating response during a service outage, this is for you.
Uses the server to automatically list all incidents, check which teams are involved, and verify the current on-call schedule when a new alert hits.
Uses the server to gather all relevant roles and incident types, ensuring every necessary person and process is accounted for during a major outage.
Uses the server to check the current list of users and teams, verifying permissions or roles before escalating a potential incident.
What Changes When You Connect
- See the full status of an outage instantly. Use
get_incidentto pull all details and history for a specific incident ID without manually navigating the UI. - Know who's responsible when the system breaks.
list_incident_rolesandlist_teamslet your agent confirm roles and team assignments instantly. - Check who's on call, right now.
list_schedulespulls all active on-call schedules, ensuring the right person gets paged when needed. - Triage faster with structured data. By using
list_severitiesandlist_incident_types, your agent classifies the event immediately, improving prioritization. - Manage incident context easily.
list_custom_fieldslets your agent know what specific data points are available to track, making your automation more precise.
Real-World Use Cases
Initial Triage for a New Outage
An alert fires. Instead of opening the dashboard and clicking through tabs, the agent runs list_incidents to get a list of active issues. It then runs get_incident on the new ID to pull the full history, severity, and initial description, giving the on-call engineer the full picture in seconds.
Confirming On-Call Coverage
A teammate asks, 'Who's covering the payment service today?' The agent executes list_schedules and checks the relevant team against list_users to provide the exact on-call contact and their current shift details.
Building an Incident Report Summary
The agent runs list_incident_types and list_incident_roles to build a structured summary for a post-mortem. It pulls the predefined structure—like severity levels—so the report is consistent and ready to submit.
Auditing User Permissions
Before a fix is deployed, the DevOps team needs to verify who can approve it. The agent uses list_users combined with list_incident_roles to check user permissions against the required role for the specific incident type.
The Tradeoffs
Over-relying on the UI
Trying to find out who is on call for a specific service requires opening the dashboard, filtering by service name, and manually scrolling through the schedule until you find the name.
→
Ask your agent to run list_schedules and filter the results by the service name. This gives you the schedule data immediately, without touching the UI.
Jumping between tabs
When a new incident pops up, you manually copy the incident ID and then switch to the 'Users' tab to check if the user is assigned a specific role, then switch to 'Types' to see the category.
→
Ask the agent to run get_incident and include the parameters for list_incident_roles and list_incident_types in the prompt. It pulls all three pieces of context in one go.
Assuming data exists
Assuming a user has the right role just because they work in the right team, without checking the system's defined permissions.
→
Always run list_incident_roles and list_users together. This confirms the user exists and that the required role is actually assigned and active for the current incident.
When It Fits, When It Doesn't
Use this server if your workflow requires combining multiple, structured data points—like linking a user, a role, a team, and an incident ID—to determine the current state of a system. For example, if you need to know: 'Show me all Critical incidents involving the Database Team assigned to Jane Doe.' This server handles that cross-referencing. Don't use it if you simply need to send a message or write a document; those are messaging or document generation tools. If you only need to list all users, list_users works fine, but using the server's context is better because it allows you to filter that list by roles or teams too.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Incident.io. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
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
Works with 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 server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Triage should never feel like detective work.
Right now, when an alert hits, you open the dashboard. You copy the incident ID. You jump to the 'Users' tab to check who is involved. Then you switch to 'Schedules' to see who's on call. You might have to copy and paste the ID into three different places just to get the full context.
With this MCP server, you tell your agent, 'What's the status of incident XYZ?' The agent runs `get_incident` and pulls the ID, the on-call schedule (`list_schedules`), and the assigned roles (`list_incident_roles`) into one structured response. It saves you 15 minutes of clicking.
Incident.io MCP Server: Get the full incident story.
You eliminate the need to manually query the 'Types' list, the 'Severities' list, and the 'Teams' list separately. You just ask the agent about the incident, and it pulls all that context into the result. The system handles the cross-referencing.
The system doesn't just give you data; it gives you the full, structured context of the event. It's all there. Period.
Common Questions About Incident.io MCP
How do I use the `list_incidents` tool to find active outages? +
Run list_incidents and filter the results by status (e.g., 'Active'). This gives you a list of all current outages. If you need details on one, run get_incident next.
Can I use `list_schedules` to find out who is on call for a specific team? +
Yes, list_schedules shows all rotations. You need to include the team name in your prompt so the agent filters the schedules down to just that team's coverage.
What is the difference between `list_users` and `list_teams`? +
list_users gives a roster of people. list_teams gives the organizational groups. You use them together to see which users belong to which teams.
How do I check if an incident has a specific severity level? +
First, run list_severities to confirm the available levels. Then, run get_incident and ask the agent to return the severity field for the specific incident ID.
How do I use `get_incident` to check the full details and history of an incident? +
The get_incident tool pulls all data—status, history, and assigned roles—for a single ID. You can then ask your agent to summarize the timeline or identify the primary owner.
Can I use `list_custom_fields` to understand what data is tracked for incidents? +
Yes, list_custom_fields provides a list of every unique data point used across your system. This lets you confirm what context your agent can gather when retrieving incident data.
What happens if I run `list_incident_roles` and it returns an empty list? +
An empty list means no roles are defined in your Incident.io setup. You'll need to check your organization's configuration to define the necessary roles first.
Is there a way to check incident status across multiple IDs using `list_incidents`? +
The list_incidents tool fetches a list of incidents, and you can instruct your agent to filter that list based on criteria like status or severity.
How do I get Incident.io API credentials? +
Log in to your Incident.io dashboard, navigate to Settings > API keys, and click 'Add new' to generate a Bearer Token.
Which version of the API is used? +
This MCP uses Incident.io API v2, the latest stable version for comprehensive incident management.
Can I see on-call schedules? +
Yes, the list_schedules tool provides access to on-call schedules and rotation information.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Grain
Manage AI meeting notes via Grain — list and search recordings, retrieve transcripts and AI insights, and track action items directly from any AI agent.
Ayanza
AI-powered project management and team collaboration — manage tasks, projects, and wikis via AI.
Pushbullet
Send files, links, and notifications between your phone and computer instantly with universal copy-paste across all devices.
You might also like
Aliyun OSS / 阿里云对象存储
China's leading object storage service — manage files, buckets, and metadata via AI.
Google Ads
Monitor and analyze Google Ads performance — track campaigns, keywords, and metrics via AI.
EPA Envirofacts (Environmental Data)
Access US environmental data including UV forecasts, facility information, and toxic release inventories directly from the EPA.