Connect incident.io to Claude Code
Read and run incidents, status updates, follow-ups, alerts, on-call schedules and escalations in incident.io. Add Toolspoke to Claude Code once and it can use 19 incident.io actions. Your incident.io credential stays in Toolspoke, and you choose which actions Claude Code may call.
Set it up in Claude Code
Three steps, the first one once for every toolkit you will ever add.
Add Toolspoke to Claude Code
Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcpThe sign-in opens in your browser, and Toolspoke asks you to approve it.
Install incident.io and connect it
Add incident.io to a project in your Toolspoke workspace.
API key. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.
- API key
- incident.io → Settings → API keys → Add new. Tick "View data" for every read here. Add "Create incidents", "Edit incidents", "Manage follow-ups", "Resolve alerts" or "Create escalations" only for the writes agents should make.
Choose what Claude Code may do
All 19 actions start on. Switch off any of the 6 actions that change something in incident.io, and Claude Code gets a refusal if it tries.
What you can ask Claude Code for
A few of the incident.io actions that only read, so they are safe to try first.
- Fetch one incident with its status, severity, roles, custom fields, timestamps and Slack channel
- List the severities configured in this organization, with their ids and ranks
- List the incident statuses configured in this organization, with their ids and categories
- List the incident types configured in this organization
What Claude Code can do in incident.io
13 actions read, 4 write and 2 delete or permanently change something.
Reads
List incidents
List incidents, newest first, filtered by status category (triage, live, learning, closed…), severity or creation time. Use list_severities and list_incident_statuses for the ids the filters take. Paginate by passing the last incident's id as after.
Get incident
Fetch one incident with its status, severity, roles, custom fields, timestamps and Slack channel. Takes the incident's id, not its INC- number.
List incident updates
The status updates posted on an incident, newest first, what responders said and how status and severity changed.
List severities
List the severities configured in this organization, with their ids and ranks.
List incident statuses
List the incident statuses configured in this organization, with their ids and categories.
List incident types
List the incident types configured in this organization.
List incident roles
List incident roles, such as incident lead, with their ids.
List follow ups
List post-incident follow-ups, optionally for one incident or team, oldest first.
List alerts
List alerts received from monitoring sources, newest first, optionally by status (firing or resolved) or alert source.
List schedules
List on-call schedules.
Get schedule
Fetch one schedule with its rotations and who is on call now.
List escalations
List escalations (pages), newest first, optionally by status or incident.
List users
List users, or find one by email. Returns names, emails and roles.
Writes
Edit incident
Change an incident's name, summary, severity or status. Only the fields given change. Set notify_incident_channel to tell responders in Slack.
Post incident update
Post a status update on an incident, optionally moving it to a new status or severity. The update is shared with responders in the incident's channel.
Create follow up
Add a follow-up to an incident.
Resolve alert
Mark one firing alert resolved. The monitoring source can fire it again.
Deletes or permanently changes
Create incident
Declare an incident. Classified destructive because it acts on people at once: incident.io opens a Slack channel, runs the organization's workflows, and can page responders and update status pages. Use mode test to try it without waking anyone. idempotency_key makes a retry return the first incident instead of declaring a second one.
Create escalation
Page people now, through an escalation path or directly by user id. Destructive because it wakes people up and cannot be unsent. idempotency_key makes a retry return the first escalation instead of paging twice.
incident.io in Claude Code: questions
Does Claude Code see my incident.io credential?
No. The credential is stored encrypted in Toolspoke, and the gateway adds it to each call. Claude Code only ever talks to Toolspoke, and the dashboard shows the last four characters of the credential and nothing more.
Can I stop Claude Code from changing things in incident.io?
Yes. Each of the 19 actions can be switched off for a project. Turn off the 6 that change something and Claude Code can only read.
Will 19 actions crowd Claude Code's context?
No. Toolspoke shows Claude Code five bridge tools, plus a guide where a toolkit has one, and Claude Code searches for the incident.io action it needs when it needs it. Adding more toolkits does not add more tools to its list.
Can I add it once for every project?
Yes. Add --scope user to the command and Claude Code keeps Toolspoke in every project on this machine. Without it, the server is added to the project you ran the command in.
What does it cost?
Tool calls are free on every plan, and a incident.io call does not run in a sandbox, so it bills nothing.
incident.io in your other apps
Try incident.io in Claude Code
Free to start, and tool calls cost nothing on any plan.