Rootly MCP server

What the model can do

Rootly incident management: incidents with status, severity, services and timeline, action items, alerts, services, severities, incident roles and users. Can declare, update, mitigate, resolve, cancel and delete incidents, assign roles and add subscribers, acknowledge, resolve, snooze and escalate alerts, add an internal timeline note, and add or update action items.

Reads

• rootly_list_incidentsRootly incidents, newest first by default: number, title, status, severity, services, teams, who opened it, start, mitigation and resolution times…
• rootly_get_incidentOne Rootly incident in full: status and every milestone time (detected, acknowledged, mitigated, resolved, closed), severity, services, environments…
• rootly_incident_timelineAn incident's timeline in Rootly: each event's text, when it happened and whether it is internal or external.
• rootly_list_action_itemsAction items (tasks and follow-ups) in Rootly: summary, kind, priority, status, due date and assignee.
• rootly_list_alertsAlerts received by Rootly: summary, status, source, services, environments, labels and times.
• rootly_list_servicesServices defined in Rootly, with their description and slug.
• rootly_list_severitiesSeverities defined in Rootly (name, slug, level) with their ids, for declaring or updating an incident.
• rootly_list_incident_rolesIncident roles defined in Rootly (Commander, Scribe and so on) with their ids, for assigning a role with rootly_assign_incident_role.
• rootly_list_usersRootly users by name, with their ids, to assign a role, an action item or subscribe them.

Acts, when you ask

These change something in Rootly. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

• rootly_add_timeline_eventAdds an event to an incident's timeline in Rootly, with internal visibility only, so it is never shown on a status page.
• rootly_create_action_itemAdds an action item (a task or a follow-up) to an incident in Rootly.
• rootly_create_incidentDeclares a new incident in Rootly, created by the API key's user.
• rootly_update_incidentChanges a Rootly incident: title, summary, status, severity, or the services, environments or teams attached (a list given replaces the list).
• rootly_mitigate_incidentMarks a Rootly incident mitigated, with an optional note of how.
• rootly_resolve_incidentResolves a Rootly incident, with an optional note of how.
• rootly_cancel_incidentCancels a Rootly incident (declared by mistake, or not an incident), with an optional reason.
• rootly_delete_incidentPermanently deletes a Rootly incident with its timeline and action items.
• rootly_assign_incident_roleAssigns an incident role (from rootly_list_incident_roles) to a Rootly user (from rootly_list_users) on an incident.
• rootly_add_incident_subscribersSubscribes Rootly users (from rootly_list_users) to an incident, so they receive its updates from now on.
• rootly_acknowledge_alertAcknowledges a Rootly alert, which stops it escalating to the next on-call level.
• rootly_resolve_alertResolves a Rootly alert, with an optional note.
• rootly_snooze_alertSnoozes a Rootly alert for a number of minutes, extending its acknowledgment timeout so it does not escalate in that time.
• rootly_escalate_alertEscalates a Rootly alert to the next level of its escalation policy (or to a given policy and level), which pages the on-call people at that level.
• rootly_update_action_itemChanges a Rootly action item: summary, description, kind, priority, status (open, in_progress, cancelled, done), due date or assignee.

Connect it

First connect Rootly on Dashboard → Connections, then add Memtro to your client once. The Rootly tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Rootly connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

• › Which action items are still open from last week's incident?
• › What happened during the checkout outage on Tuesday, in order?
• › How long did it take to mitigate the last SEV1?
• › Which alerts came in overnight, and from which source?
• › Resolve the Northwind outage incident with a note that the retry fix is deployed

Questions

Is this an official Rootly MCP server?

No. It is Memtro's MCP server with Memtro's Rootly connector behind it: the connector reads Rootly through its API with the credentials you connect on Dashboard → Connections, and Rootly publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

What does it cost?

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in Rootly?

Only when you ask, and only what it has been granted: add an internal event to an incident's timeline; add an action item to an incident; declare an incident (your Rootly workflows may page responders and open a channel); update an incident's title, summary, status, severity, services, environments or teams; mark an incident mitigated; resolve an incident; cancel an incident; delete an incident (permanent); assign an incident role to a user; subscribe users to an incident's updates; acknowledge an alert (stops its escalation); resolve an alert; snooze an alert for some minutes; escalate an alert (pages the next on-call level); update an action item's summary, status, priority, due date or assignee. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.

Which clients work?

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

Other MCP servers · Engineering and operations

• GitHub MCP server
• AWS CloudWatch MCP server
• Sentry MCP server
• ServiceNow MCP server
• Okta MCP server
• Twilio MCP server