Skip to content

Connectors · Service desk & support

incident.io MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to incident.io and the rest of your systems. It gives your agent 326 incident.io actions (148 reads, 128 writes and 50 that wait for a confirmation) and holds the incident.io credential itself, so the agent never does. It paces incident.io's limits and records every call.

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp
the first call
do {  action: "incident_io.users.list",  intent: "check which incident.io account is connected"}# List Users V2 · read · 1 upstream call
  • 326actionsin one signed file
  • 148readlook, never change
  • 128writecreate and update
  • 50wait for a yesdestructive, confirmed first

Set up

Connect incident.io in three steps.

  1. 01

    Add actionlake to Claude.

    Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.

    https://connect.actionlake.com/mcp
  2. 02

    Connect incident.io.

    Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.

    • api_keyincident.io API key
    account { op: "connections.requirements", service: "incident_io" }
    # free: exactly what to paste, and what is found for you
  3. 03

    Make the first call. Check before a write.

    Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

    do    { action: "incident_io.users.list" }# list users v2 · read · 1 upstream callcheck { action: "incident_io.schedules.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

incident.io at a glance

Sign-in
Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide
api_key
Limits we pace to
1,200 calls a minute, per connection
API covered
Incident.io public API v1/v2/v3 (OpenAPI 3.0.3, openapiV3.json)api.incident.io
Built from
incident.io's documentation, read 22 October 2026api.incident.ioapi-docs.incident.io
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
144 of 148 reads, for up to 5 minutes; a write clears what it affects
Shared entities
4, so ask can line incident.io up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in incident.io.

326 actions in 92 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 148readlook, never change
  • 128writecreate and update
  • 50destructivewait for a confirmation
  1. Escalations

    7

    3 read · 3 write · 1 destructive

    CheckEscalationPermissions Escalations V2 · Create Escalations V2 · List Escalations V2 · Show Escalations V2

  2. Follow ups

    7

    2 read · 4 write · 1 destructive

    Create Follow-ups V3 · CreateFromLink Follow-ups V3 · List Follow-ups V3 · ConnectExternalIssue Follow-ups V3

  3. Alert sources

    6

    3 read · 2 write · 1 destructive

    Create Alert Sources V2 · List Alert Sources V2 · Validate Alert Sources V2 · Show Alert Sources V2

  4. Alerts

    6

    2 read · 4 write · 0 destructive

    List Alerts V2 · Show Alerts V2 · AddTags Alerts V2 · RemoveTags Alerts V2

  5. API keys

    6

    2 read · 2 write · 2 destructive

    Create API Keys V1 · List API Keys V1 · Show API Keys V1 · Rotate API Keys V1

  6. Catalog entries

    6

    2 read · 3 write · 1 destructive

    CreateEntry Catalog V3 · ListEntries Catalog V3 · BulkUpdateEntries Catalog V3 · ShowEntry Catalog V3

  7. Catalog types

    6

    2 read · 3 write · 1 destructive

    CreateType Catalog V3 · ListTypes Catalog V3 · ShowType Catalog V3 · UpdateType Catalog V3

  8. Catalog types V2

    6

    2 read · 3 write · 1 destructive

    CreateType Catalog V2 · ListTypes Catalog V2 · ShowType Catalog V2 · UpdateType Catalog V2

84 more areas · 276 actions
  • Follow ups V2 6
  • Incident templates 6
  • Pay reports 6
  • Schedules 6
  • Secrets 6
  • Actions 5
  • Actions V2 5
  • Alert attributes 5
  • Alert notes 5
  • Alert routes 5
  • Alert routes V2 5
  • Announcement rules 5
  • Announcement templates 5
  • Call route allowed callers 5
  • Call route options 5
  • Catalog entries V2 5
  • Custom field options 5
  • Custom fields 5
  • Custom fields V1 5
  • Escalation path templates 5
  • Escalation paths 5
  • Incident forms 5
  • Incident roles 5
  • Incident roles V1 5
  • Incident statuses 5
  • Incidents 5
  • Maintenance windows 5
  • Pay config one off rules 5
  • Pay config weekly rules 5
  • Pay configs 5
  • Policies 5
  • Schedule overrides 5
  • Schedule sync rules 5
  • Schedule sync targets 5
  • Severities 5
  • Status page components 5
  • Status page maintenances 5
  • Workflows 5
  • Policy findings 4
  • Postmortem documents 4
  • Schedule replicas 4
  • Status page incidents 4
  • Call routes 3
  • Incident alerts 3
  • Incident attachments 3
  • Incident timeline items 3
  • Incidents V1 3
  • Actions V1 2
  • Incident memberships 2
  • Incident team memberships 2
  • Incident timestamps 2
  • Incident types 2
  • Incident updates 2
  • Ip allowlists 2
  • On call notification pauses 2
  • Status pages 2
  • Teams 2
  • User paging provider 2
  • Users 2
  • Workflow runs 2
  • Alert events HTTP 1
  • Alert tags 1
  • Call sessions 1
  • Call transcript entries 1
  • Catalog resources 1
  • Catalog resources V2 1
  • Heartbeat ping 1
  • Identity 1
  • Incident activity log entries 1
  • Incident participant workloads 1
  • Incident participants 1
  • Incident relationships 1
  • Ip ranges 1
  • Postmortem document content 1
  • Schedule entries 1
  • Status page component availability 1
  • Status page incident response incidents 1
  • Status page incident updates 1
  • Status page maintenance updates 1
  • Status page retrospective incidents 1
  • Status page structures 1
  • Telemetry data sources 1
  • User notification methods 1
  • User notification rules 1

Top actions

The incident.io API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 43 of incident.io's 48 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
incident_io.users.listList Users V2List Users V2.readidentity.user.list474 connectors
incident_io.teams.listList Teams V3List Teams V3.readidentity.group.list262 connectors
incident_io.alerts.listList Alerts V2List Alerts V2.readmonitoring.alert.list51 connectors
incident_io.users.getShow Users V2Show Users V2.readidentity.user.get399 connectors
incident_io.incidents.listList Incidents V2List Incidents V2.readmonitoring.incident.list19 connectors
incident_io.teams.getShow Teams V3Show Teams V3.readidentity.group.get212 connectors
incident_io.schedules.listList Schedules V2List Schedules V2.readhr.on_call_schedule.list11 connectors
incident_io.schedules.createCreate Schedules V2Create Schedules V2.writehr.on_call_schedule.create11 connectors
incident_io.escalation_paths.createCreatePath Escalations V2CreatePath Escalations V2.writehr.escalation_policy.create11 connectors
incident_io.escalation_paths.listListPaths Escalations V2ListPaths Escalations V2.readhr.escalation_policy.list10 connectors
incident_io.incidents.createCreate Incidents V2Create Incidents V2.writemonitoring.incident.create13 connectors
incident_io.schedules.deleteDestroy Schedules V2Destroy Schedules V2.destructivehr.on_call_schedule.delete11 connectors

Try it

Prompts to paste into Claude.

Each one names the incident.io actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    Which incident.io incidents are open, and how long has each been open?

    callsincident_io.incidents.list

  2. Writewrite

    Create Schedules V2 in incident.io. Show me exactly what you will send before you save it.

    callsincident_io.schedules.create

Governance for incident.io

Destructive actions wait for a yes.

50 incident.io actions are destructive. The first 10:

  • Destroy Schedules V2incident_io.schedules.delete
  • DestroyPath Escalations V2incident_io.escalation_paths.delete
  • DestroyWorkflow Workflows V2incident_io.workflows.delete
  • DestroyOverride Schedules V2incident_io.schedule_overrides.delete
  • Destroy Status Page Components V2incident_io.status_page_components.delete
  • Rotate Secrets V2incident_io.secrets.rotate
  • Rotate API Keys V1incident_io.api_keys.rotate
  • Delete Actions V3incident_io.actions.delete
  • Destroy Secrets V2incident_io.secrets.delete
  • Delete API Keys V1incident_io.api_keys.delete

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

doincident_io.schedules.deleteconfirm_policy: human

Destroy Schedules V2?

intent: the user asked me to destroy Schedules V2

run suspended · waiting for a named person · key incident-io-agent cannot confirm itself
In the console, or from an emailed signed link.
a key for this connector
account {  op: "keys.create", name: "incident-io-agent",  allowed_actions: ["incident_io.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "incident_io.schedules.delete", approver: "[email protected]" },    { match: "incident_io.escalation_paths.delete", approver: "[email protected]" },    { match: "incident_io.workflows.delete", approver: "[email protected]" }  ]}
Illustrative. Scoped to incident.io only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What incident.io costs on actionlake.

Every incident.io action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call incident.io refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

  • 1upstream call per actionall 326 incident.io actions
  • 326actions pageeach page of a long list is one call
  • 144reads can be cacheda cache hit costs nothing
  • 100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every incident.io action.

326 actions by area: the id your agent calls, what it does, and its effect.

Escalations7
  • incident_io.escalations.check_permissionsCheckEscalationPermissions Escalations V2read
  • incident_io.escalations.createCreate Escalations V2write
  • incident_io.escalations.getShow Escalations V2read
  • incident_io.escalations.listList Escalations V2read
  • incident_io.escalations.cancelCancelEscalation Escalations V2destructive
  • incident_io.escalations.reassignReassignEscalation Escalations V2write
  • and 1 more in this area
Follow ups7
  • incident_io.follow_ups.connect_external_issueConnectExternalIssue Follow-ups V3write
  • incident_io.follow_ups.createCreate Follow-ups V3write
  • incident_io.follow_ups.create_from_linkCreateFromLink Follow-ups V3write
  • incident_io.follow_ups.listList Follow-ups V3read
  • incident_io.follow_ups.deleteDelete Follow-ups V3destructive
  • incident_io.follow_ups.getShow Follow-ups V3read
  • and 1 more in this area
Alert sources6
  • incident_io.alert_sources.createCreate Alert Sources V2write
  • incident_io.alert_sources.getShow Alert Sources V2read
  • incident_io.alert_sources.listList Alert Sources V2read
  • incident_io.alert_sources.validateValidate Alert Sources V2read
  • incident_io.alert_sources.deleteDelete Alert Sources V2destructive
  • incident_io.alert_sources.updateUpdate Alert Sources V2write
Alerts6
  • incident_io.alerts.add_tagsAddTags Alerts V2write
  • incident_io.alerts.getShow Alerts V2read
  • incident_io.alerts.listList Alerts V2read
  • incident_io.alerts.remove_tagsRemoveTags Alerts V2write
  • incident_io.alerts.resolveResolve Alerts V2write
  • incident_io.alerts.set_tagsSetTags Alerts V2write
API keys6
  • incident_io.api_keys.createCreate API Keys V1write
  • incident_io.api_keys.getShow API Keys V1read
  • incident_io.api_keys.listList API Keys V1read
  • incident_io.api_keys.rotateRotate API Keys V1destructive
  • incident_io.api_keys.deleteDelete API Keys V1destructive
  • incident_io.api_keys.updateUpdate API Keys V1write
Catalog entries6
  • incident_io.catalog_entries.bulk_updateBulkUpdateEntries Catalog V3write
  • incident_io.catalog_entries.createCreateEntry Catalog V3write
  • incident_io.catalog_entries.getShowEntry Catalog V3read
  • incident_io.catalog_entries.listListEntries Catalog V3read
  • incident_io.catalog_entries.deleteDestroyEntry Catalog V3destructive
  • incident_io.catalog_entries.updateUpdateEntry Catalog V3write
Catalog types6
  • incident_io.catalog_types.createCreateType Catalog V3write
  • incident_io.catalog_types.getShowType Catalog V3read
  • incident_io.catalog_types.listListTypes Catalog V3read
  • incident_io.catalog_types.updateUpdateType Catalog V3write
  • incident_io.catalog_types.deleteDestroyType Catalog V3destructive
  • incident_io.catalog_types.update_schemaUpdateTypeSchema Catalog V3write
Catalog types V26
  • incident_io.catalog_types_v2.createCreateType Catalog V2write
  • incident_io.catalog_types_v2.getShowType Catalog V2read
  • incident_io.catalog_types_v2.listListTypes Catalog V2read
  • incident_io.catalog_types_v2.updateUpdateType Catalog V2write
  • incident_io.catalog_types_v2.deleteDestroyType Catalog V2destructive
  • incident_io.catalog_types_v2.update_schemaUpdateTypeSchema Catalog V2write
Follow ups V26
  • incident_io.follow_ups_v2.connect_external_issueConnectExternalIssue Follow-ups V2write
  • incident_io.follow_ups_v2.createCreate Follow-ups V2write
  • incident_io.follow_ups_v2.getShow Follow-ups V2read
  • incident_io.follow_ups_v2.listList Follow-ups V2read
  • incident_io.follow_ups_v2.deleteDelete Follow-ups V2destructive
  • incident_io.follow_ups_v2.updateUpdate Follow-ups V2write
Incident templates6
  • incident_io.incident_templates.createCreate Incident Templates V1write
  • incident_io.incident_templates.getShow Incident Templates V1read
  • incident_io.incident_templates.listList Incident Templates V1read
  • incident_io.incident_templates.validateValidate Incident Templates V1read
  • incident_io.incident_templates.deleteDestroy Incident Templates V1destructive
  • incident_io.incident_templates.updateUpdate Incident Templates V1write
Pay reports6
  • incident_io.pay_reports.createCreate Pay Reports V2write
  • incident_io.pay_reports.getShow Pay Reports V2read
  • incident_io.pay_reports.listList Pay Reports V2read
  • incident_io.pay_reports.publishPublish Pay Reports V2write
  • incident_io.pay_reports.deleteDestroy Pay Reports V2destructive
  • incident_io.pay_reports.unpublishUnpublish Pay Reports V2write
Schedules6
  • incident_io.schedules.createCreate Schedules V2write
  • incident_io.schedules.getShow Schedules V2read
  • incident_io.schedules.listList Schedules V2read
  • incident_io.schedules.updateUpdate Schedules V2write
  • incident_io.schedules.deleteDestroy Schedules V2destructive
  • incident_io.schedules.preview_entriesPreviewScheduleEntries Schedules V2read
Secrets6
  • incident_io.secrets.createCreate Secrets V2write
  • incident_io.secrets.getShow Secrets V2read
  • incident_io.secrets.listList Secrets V2read
  • incident_io.secrets.rotateRotate Secrets V2destructive
  • incident_io.secrets.deleteDestroy Secrets V2destructive
  • incident_io.secrets.updateUpdate Secrets V2write
Actions5
  • incident_io.actions.createCreate Actions V3write
  • incident_io.actions.getShow Actions V3read
  • incident_io.actions.listList Actions V3read
  • incident_io.actions.updateUpdate Actions V3write
  • incident_io.actions.deleteDelete Actions V3destructive
Actions V25
  • incident_io.actions_v2.createCreate Actions V2write
  • incident_io.actions_v2.getShow Actions V2read
  • incident_io.actions_v2.listList Actions V2read
  • incident_io.actions_v2.updateUpdate Actions V2write
  • incident_io.actions_v2.deleteDelete Actions V2destructive
Alert attributes5
  • incident_io.alert_attributes.createCreate Alert Attributes V2write
  • incident_io.alert_attributes.getShow Alert Attributes V2read
  • incident_io.alert_attributes.listList Alert Attributes V2read
  • incident_io.alert_attributes.updateUpdate Alert Attributes V2write
  • incident_io.alert_attributes.deleteDestroy Alert Attributes V2destructive
Alert notes5
  • incident_io.alert_notes.createCreate Alert Notes V1write
  • incident_io.alert_notes.getShow Alert Notes V1read
  • incident_io.alert_notes.listList Alert Notes V1read
  • incident_io.alert_notes.updateUpdate Alert Notes V1write
  • incident_io.alert_notes.deleteDelete Alert Notes V1destructive
Alert routes5
  • incident_io.alert_routes.createCreate Alert Routes V3write
  • incident_io.alert_routes.getShow Alert Routes V3read
  • incident_io.alert_routes.listList Alert Routes V3read
  • incident_io.alert_routes.updateUpdate Alert Routes V3write
  • incident_io.alert_routes.deleteDelete Alert Routes V3destructive
Alert routes V25
  • incident_io.alert_routes_v2.createCreate Alert Routes V2write
  • incident_io.alert_routes_v2.getShow Alert Routes V2read
  • incident_io.alert_routes_v2.listList Alert Routes V2read
  • incident_io.alert_routes_v2.updateUpdate Alert Routes V2write
  • incident_io.alert_routes_v2.deleteDelete Alert Routes V2destructive
Announcement rules5
  • incident_io.announcement_rules.createCreate Announcement Rules V2write
  • incident_io.announcement_rules.getShow Announcement Rules V2read
  • incident_io.announcement_rules.listList Announcement Rules V2read
  • incident_io.announcement_rules.updateUpdate Announcement Rules V2write
  • incident_io.announcement_rules.deleteDestroy Announcement Rules V2destructive
Announcement templates5
  • incident_io.announcement_templates.createCreate Announcement Templates V2write
  • incident_io.announcement_templates.getShow Announcement Templates V2read
  • incident_io.announcement_templates.listList Announcement Templates V2read
  • incident_io.announcement_templates.updateUpdate Announcement Templates V2write
  • incident_io.announcement_templates.deleteDestroy Announcement Templates V2destructive
Call route allowed callers5
  • incident_io.call_route_allowed_callers.createCreateAllowedCaller Call Routes V2write
  • incident_io.call_route_allowed_callers.getShowAllowedCaller Call Routes V2read
  • incident_io.call_route_allowed_callers.listListAllowedCallers Call Routes V2read
  • incident_io.call_route_allowed_callers.updateUpdateAllowedCaller Call Routes V2write
  • incident_io.call_route_allowed_callers.deleteDestroyAllowedCaller Call Routes V2destructive
Call route options5
  • incident_io.call_route_options.createCreateOption Call Routes V2write
  • incident_io.call_route_options.getShowOption Call Routes V2read
  • incident_io.call_route_options.listListOptions Call Routes V2read
  • incident_io.call_route_options.updateUpdateOption Call Routes V2write
  • incident_io.call_route_options.deleteDestroyOption Call Routes V2destructive
Catalog entries V25
  • incident_io.catalog_entries_v2.createCreateEntry Catalog V2write
  • incident_io.catalog_entries_v2.getShowEntry Catalog V2read
  • incident_io.catalog_entries_v2.listListEntries Catalog V2read
  • incident_io.catalog_entries_v2.updateUpdateEntry Catalog V2write
  • incident_io.catalog_entries_v2.deleteDestroyEntry Catalog V2destructive
Custom field options5
  • incident_io.custom_field_options.createCreate Custom Field Options V1write
  • incident_io.custom_field_options.getShow Custom Field Options V1read
  • incident_io.custom_field_options.listList Custom Field Options V1read
  • incident_io.custom_field_options.updateUpdate Custom Field Options V1write
  • incident_io.custom_field_options.deleteDelete Custom Field Options V1destructive
Custom fields5
  • incident_io.custom_fields.createCreate Custom Fields V2write
  • incident_io.custom_fields.getShow Custom Fields V2read
  • incident_io.custom_fields.listList Custom Fields V2read
  • incident_io.custom_fields.updateUpdate Custom Fields V2write
  • incident_io.custom_fields.deleteDelete Custom Fields V2destructive
Custom fields V15
  • incident_io.custom_fields_v1.createCreate Custom Fields V1write
  • incident_io.custom_fields_v1.getShow Custom Fields V1read
  • incident_io.custom_fields_v1.listList Custom Fields V1read
  • incident_io.custom_fields_v1.updateUpdate Custom Fields V1write
  • incident_io.custom_fields_v1.deleteDelete Custom Fields V1destructive
Escalation path templates5
  • incident_io.escalation_path_templates.createCreate Escalation Path Templates V2write
  • incident_io.escalation_path_templates.getShow Escalation Path Templates V2read
  • incident_io.escalation_path_templates.listList Escalation Path Templates V2read
  • incident_io.escalation_path_templates.updateUpdate Escalation Path Templates V2write
  • incident_io.escalation_path_templates.deleteDestroy Escalation Path Templates V2destructive
Escalation paths5
  • incident_io.escalation_paths.createCreatePath Escalations V2write
  • incident_io.escalation_paths.getShowPath Escalations V2read
  • incident_io.escalation_paths.listListPaths Escalations V2read
  • incident_io.escalation_paths.updateUpdatePath Escalations V2write
  • incident_io.escalation_paths.deleteDestroyPath Escalations V2destructive
Incident forms5
  • incident_io.incident_forms.createCreate Incident Forms V3write
  • incident_io.incident_forms.getShow Incident Forms V3read
  • incident_io.incident_forms.listList Incident Forms V3read
  • incident_io.incident_forms.updateUpdate Incident Forms V3write
  • incident_io.incident_forms.deleteDelete Incident Forms V3destructive

Incident roles 5Incident roles V1 5Incident statuses 5Incidents 5Maintenance windows 5Pay config one off rules 5Pay config weekly rules 5Pay configs 5Policies 5Schedule overrides 5Schedule sync rules 5Schedule sync targets 5Severities 5Status page components 5Status page maintenances 5Workflows 5Policy findings 4Postmortem documents 4Schedule replicas 4Status page incidents 4Call routes 3Incident alerts 3Incident attachments 3Incident timeline items 3Incidents V1 3Actions V1 2Incident memberships 2Incident team memberships 2Incident timestamps 2Incident types 2Incident updates 2Ip allowlists 2On call notification pauses 2Status pages 2Teams 2User paging provider 2Users 2Workflow runs 2Alert events HTTP 1Alert tags 1Call sessions 1Call transcript entries 1Catalog resources 1Catalog resources V2 1Heartbeat ping 1Identity 1Incident activity log entries 1Incident participant workloads 1Incident participants 1Incident relationships 1Ip ranges 1Postmortem document content 1Schedule entries 1Status page component availability 1Status page incident response incidents 1Status page incident updates 1Status page maintenance updates 1Status page retrospective incidents 1Status page structures 1Telemetry data sources 1User notification methods 1User notification rules 1

This index shows a sample of each area. All 326 actions, with their inputs and prices, are in the catalogue, which a free sandbox key can search.

Questions

The incident.io MCP server, answered.

Is there an incident.io MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 326 incident.io actions across escalations, follow ups, alert sources and alerts, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by incident.io.

What do I need to connect incident.io?

Incident.io API key. The free call account { op: "connections.requirements", service: "incident_io" } lists exactly what to paste.

Can an AI agent delete or change things in incident.io?

Only if its key allows it, and only with an explicit confirmation. 50 incident.io actions are destructive, including destroy Schedules V2, destroyPath Escalations V2 and destroyWorkflow Workflows V2. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my incident.io API limit?

actionlake paces every call to the limits in the incident.io service file: 1,200 calls a minute per connection. Repeated reads are answered from cache (144 incident.io actions can be), which never reaches incident.io.

What does an incident.io action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (326 incident.io actions page). Cache hits, searches, dry runs and calls incident.io refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which incident.io API does it cover?

The incident.io public API v1/v2/v3 (OpenAPI 3.0.3, openapiV3.json) at api.incident.io. It is built from incident.io's documentation as read on 22 October 2026. 326 actions in 92 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my incident.io data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your incident.io credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

Give your agent incident.io today.

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.