incident.io for AI agents

incident.io is an incident management and response platform for declaring, tracking, and resolving operational incidents. Engineering teams pull it into internal tools and scripts rather than building the same capability themselves. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect incident.io See the 86 actions ↓

Developer toolsAPI keyMCP + RESTincident.io

AUDIT LOG · INCIDENT.IOPOLICY: acme-support

09:41:07 · claude · u_8f2read

incident_io.list_users_v2

List Users V2✓ allowed · 212ms

09:41:08 · claude · u_8f2read

incident_io.get_users_v2

Get User V2✓ allowed · 164ms

09:41:09 · claude · u_8f2write

incident_io.create_incidents_v2

Create Incident V2✓ approved · approved by user

09:41:12 · claude · u_8f2destructive

incident_io.delete_severity

Delete Severity✕ blocked · policy: deny

EVERY INCIDENT.IO CALL, ON THE RECORD

01 · USE CASES

What agents do in incident.io.

Declare a new incident

Create a new incident record with a severity and summary when an outage is reported.

Update an incident's status

Update an active incident's status as the team makes progress toward resolution.

Delete a severity level with confirmation

Delete a custom severity level only after a team lead confirms it is no longer used.

02 · ACTIONS

86 incident.io actions, graded by risk.

Every incident.io action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

Look things up. Allowed by default.

incident_io.get_users_v2
Get User V2
incident_io.list_users_v2
List Users V2
incident_io.list_alerts_v2
List Alerts V2
incident_io.get_incident_v2
Get Incident by ID (V2)
incident_io.list_actions_v1
List Actions V1
incident_io.list_actions_v2
List Actions V2
incident_io.get_schedules_v2
Show Schedules V2
incident_io.get_workflows_v2
Get Workflow V2
incident_io.list_identity_v1
Get API Key Identity
incident_io.get_incident_type
Get Incident Type
incident_io.get_severities_v1
Get Severity V1
incident_io.list_incidents_v2
List Incidents V2
incident_io.list_schedules_v2
List Schedules V2
incident_io.list_workflows_v2
List Workflows V2
incident_io.get_escalations_v2
Show Escalations V2
incident_io.list_follow_ups_v2
List Follow-ups V2

+ 27 MORE

write

Create and change things. Allow, or ask the user first.

incident_io.create_incidents_v2
Create Incident V2
incident_io.update_schedules_v2
Update Schedule V2
incident_io.update_workflows_v2
Update Workflow V2
incident_io.create_severities_v1
Create Severity
incident_io.update_severities_v1
Update Severity
incident_io.create_escalations_v2
Create Escalation V2
incident_io.create_alert_routes_v2
Create Alert Route V2
incident_io.create_incident_status
Create Incident Status
incident_io.update_incident_status
Update Incident Status
incident_io.create_alert_sources_v2
Create Alert Source V2
incident_io.create_catalog_types_v3
Create Catalog Type V3
incident_io.create_custom_fields_v2
Create Custom Field V2
incident_io.update_alert_sources_v2
Update Alert Source V2
incident_io.update_catalog_types_v3
Update Catalog Type V3
incident_io.update_custom_fields_v1
Update Custom Fields V1
incident_io.update_custom_fields_v2
Update Custom Field V2

+ 13 MORE

destructive

Delete, cancel or archive. Ask first, or deny outright.

incident_io.delete_severity
Delete Severity
incident_io.delete_custom_field
Delete Custom Field
incident_io.delete_schedules_v2
Delete Schedule V2
incident_io.delete_workflows_v2
Delete Workflow V2
incident_io.delete_alert_routes_v2
Delete Alert Route V2
incident_io.delete_alert_sources_v2
Delete Alert Source V2
incident_io.delete_catalog_types_v3
Delete Catalog Type V3
incident_io.delete_custom_fields_v2
Delete Custom Field V2
incident_io.delete_incident_roles_v2
Delete Incident Role V2
incident_io.delete_catalog_entries_v3
Delete Catalog Entry V3
incident_io.delete_incident_status_v1
Delete Incident Status V1
incident_io.delete_alert_attributes_v2
Delete Alert Attribute V2
incident_io.delete_escalation_paths_v2
Delete Escalation Path V2
incident_io.delete_custom_field_options_v1
Delete Custom Field Option

03 · HOW IT WORKS

incident.io in three steps.

01Your users connect incident.ioThey add their incident.io api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, writes like “create Incident V2” can wait for the user, and “delete Severity” can be denied outright.
03Any agent can actYour agent calls incident.io through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.

POLICY.TS

await arc0.policies.set('incident_io', {
  read: 'allow',
  write: 'ask',        // create_incidents_v2
  destructive: 'deny',  // delete_severity
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2

04 · AUTH AND DATA

How incident.io connects.

Users add their incident.io api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same incident.io connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH: API key
CREDENTIALS: Per-tenant encrypted vault
MODEL SEES: Results only, never credentials
AUDIT LOG: Every call, on every plan

05 · WORKS WITH

Use incident.io from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

More developer tools apps.

Addressfinder17 actions

Addresszen2 actions

Alchemy36 actions

ALL DEVELOPER TOOLS APPS →

07 · FAQ

incident.io and Arc0, answered.

Q01

Can I use incident.io with Claude, ChatGPT or Cursor?

Yes. Connect incident.io to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the incident.io actions you allow.

Q02

How do users connect incident.io?

Users add their incident.io api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which incident.io actions can my agent take?

86 in total: 43 read, 29 write and 14 destructive, such as “create Incident V2”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in incident.io?

Yes. Actions like “delete Severity” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call incident.io too?

Yes. The same incident.io connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug incident.io into your agent.

Your users connect incident.io once, under your brand. Your agent gets 86 actions behind your policies, with every call on the record.

Connect incident.io Browse all apps →

Free to build · MCP + REST · Audit log on every plan