Provider REST API

19 actions

Connect Claude to incident.io

Read and run incidents, status updates, follow-ups, alerts, on-call schedules and escalations in incident.io. Toolspoke puts 19 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: API key
Actions exposed: 19
What a call bills: Nothing
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install incident.io
Open the marketplace in your workspace, add incident.io to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with api key. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. incident.io shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What incident.io asks for

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 keyRequired: 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.; inc_…

What Claude can do in incident.io

19 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 13Reads
Writes: 4Writes
Destructive: 2Destructive

Reads

Fetches data and changes nothing.

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

Creates or updates something on the other side.

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.

Destructive

Deletes or permanently alters something. Worth granting on purpose.

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.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 19 actions above are the whole of it. A call to any other name is refused before it reaches incident.io rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It reaches no further than your credential: Toolspoke holds no access to incident.io of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from incident.io: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in incident.io. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around incident.io's own rate limits. A call that incident.io refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in incident.io?

19 named actions: 13 that only read, 4 that write and 2 that delete or permanently alter something. They include list_incidents, get_incident and list_incident_updates. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the incident.io connector need?

API key. The connector asks for api key. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the incident.io connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 19 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the incident.io connector not do?

The 19 actions above are the whole of it. A call to any other name is refused before it reaches incident.io rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Toolspoke holds no access to incident.io of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in incident.io. An agent has to ask. Toolspoke does not retry, queue or back off around incident.io's own rate limits. A call that incident.io refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches incident.io's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls incident.io?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More developer tools connectors

Browse all of them