# Incident.io MCP for AI Agents AI Agent Connect > Incident.io lets you manage the entire lifecycle of your production incidents. It gives your AI agent the ability to list active incidents, manage roles, track custom fields, and check on-call schedules. It's built for SREs and DevOps teams who need to automate incident coordination and keep their response workflows organized without manual data entry. ## Overview - **Category:** collaboration - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_SYXytajPn2E8oSQTe6uxrJcvhwsU2x1pHkOPCe4y/ai-agent-connect - **Tags:** incident-response, sre, on-call-scheduling, workflow-automation, alerting, team-coordination ## Description When a production outage hits, the last thing you want to do is manually toggle between browser tabs to find out who's on call or what the current severity of an incident is. This Connector changes that by giving your AI agent direct access to your Incident.io data. Instead of hunting for information, you can just ask your agent to summarize the current situation or identify which team needs to step in. It handles the heavy lifting of navigating your incident types, severities, and custom fields so your team can focus on actually fixing the problem. By connecting this to your workflow through Vinkius, you're putting your incident response on autopilot. You can automate the routine parts of coordination, like checking team availability or listing ongoing issues, while keeping a clean record of every custom field and role involved. It's about moving from reactive firefighting to a structured, automated response where the data is always at your fingertips. ## Tools ### get_incident Pull up the full details for a specific incident. This is useful for getting a deep dive into a single issue's history. ### list_catalog_types Shows all the defined catalog types in your system. Use this to see the categories of issues you're tracking. ### list_custom_fields Lists every custom field you've set up. This helps your agent know exactly what data points it can query for you. ### list_incident_roles Lists all the incident roles you've defined. It helps in understanding who needs to do what during a response. ### list_incident_types Shows all the incident types you use. This is great for categorizing and filtering ongoing issues. ### list_incidents Lists all incidents currently in your system. Use this to get a high-level view of everything that needs attention. ### list_schedules Lists all on-call schedules. This is the fastest way to see who's currently on the clock. ### list_severities Lists all defined incident severities. This helps the agent understand the priority levels of different issues. ### list_teams Lists all the teams in your organization. It helps in identifying the correct group to notify. ### list_users Lists all the users in your system. Use this to verify who has access or is part of the response group. ## Prompt Examples **Prompt:** ``` Who is on call for the payment gateway right now? ``` **Response:** ``` Here is the current on-call status for the **Payment Gateway** service: | Team | Responder | Shift Status | | :--- | :--- | :--- | | Payments | **Alex Rivera** | Active (Ends 08:00 UTC) | | Gateway | **Jordan Smith** | Active (Ends 12:00 UTC) | *Note: Both responders are currently active on the primary rotation.* ``` **Prompt:** ``` List all high severity incidents from the last hour. ``` **Response:** ``` I found **3 high-severity incidents** reported in the last hour: * **INC-9928**: Database Latency Spike (Severity: Critical) * **INC-9934**: Auth Service Timeout (Severity: High) * **INC-9941**: Checkout Page 500 Errors (Severity: High) Would you like me to pull the details for any of these? ``` **Prompt:** ``` What are the custom fields for our 'Database' incident type? ``` **Response:** ``` The following custom fields are defined for **Database** incident types: * `db_cluster_id` * `read_replica_status` * `primary_node_health` * `failover_triggered` I can help you fill these out or query them for specific incidents. ``` ## Capabilities ### List active incidents See every ongoing issue in your system at a glance. ### Check on-call schedules Find out who is currently responsible for a specific service. ### Manage incident roles Assign and track specific responsibilities for different people during a crisis. ### Retrieve incident details Get a full history and status update for a specific incident ID. ### View custom fields Access specific data points tailored to your unique organization needs. ### List team members Quickly identify which people belong to specific engineering or support teams. ## Use Cases ### The 'Who's on call?' panic An engineer gets paged and asks the agent to check list_schedules for the database team to see who's active. ### The 'What's the status?' request A manager asks for a summary of all high-severity issues, and the agent uses list_incidents and list_severities. ### The 'Who is doing what?' check An Incident Commander asks the agent to list the roles for a specific incident to see if a comms lead is assigned. ### The 'New incident' setup An SRE asks the agent to list the available incident types to ensure they're categorizing a new outage correctly. ## Benefits - Faster incident triage: Use list_incidents and list_severities to get an instant overview of high-priority issues. - Automated on-call lookups: Quickly find the right person to contact using list_schedules without leaving your chat. - Consistent role assignment: Ensure every incident has the right people involved by checking list_incident_roles. - Custom data access: Query your specific organizational data using list_custom_fields to get tailored answers. - Reduced manual overhead: Stop copy-pasting team info by using list_teams and list_users to identify stakeholders. ## How It Works The bottom line is you get a hands-free way to query and manage your incident response data. 1. Connect your Incident.io API keys to your AI client via Vinkius. 2. Ask your agent to perform actions like listing active incidents or finding the on-call person for a service. 3. Get a structured summary of the status, roles, and schedules directly in your chat. ## Frequently Asked Questions **Can the Incident.io MCP help me find out who is on call?** Yes, it pulls live schedules directly from your Incident.io account. This lets your agent tell you exactly who is responsible for a service in real time. **How does Incident.io MCP help with SRE workflows?** It automates the data retrieval part of incident response. Instead of clicking through dashboards, your agent can pull incident lists and severities instantly. **Can I use Incident.io MCP to see my team's roles?** Yes, it can list all defined incident roles. This helps ensure everyone knows their specific responsibilities during a response. **Does Incident.io MCP show me my custom incident fields?** It does. The Connector can list all defined custom fields, allowing your agent to understand and retrieve the specific data points your team tracks. **Can the Incident.io MCP list all active incidents at once?** Yes, it can fetch a full list of all incidents. This is great for getting a high-level overview of what's currently happening in production. **Is Incident.io MCP good for incident response coordination?** It's a great tool for coordination because it provides a fast way to query live data, like on-call schedules and team info, during a crisis. **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 Connector 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.