Your AI

Cursor and Claude trace from the map

The Kitomer MCP gives an AI client the same places, heartbeats, on-call, and incidents you see in the portal, signed in as you. Writes follow the same roles as the portal.

AI Connections in the portal: buttons to add Kitomer to Cursor, Claude, OpenAI, Bolt, Lovable, Replit, and Base44, who has connected, and the MCP endpoint
  • One sign-in. The client signs in with your Kitomer account and acts as you.
  • Your access level applies. An observer’s AI can read; a member’s can acknowledge and declare; an admin’s can edit places and policies.
  • Kitomer does not deploy, and it does not change secrets.

Connect

Open AI Connections in the portal and press the button for your client: Cursor, Claude, OpenAI, Bolt, Lovable, Replit, or Base44. Your browser asks you to authorize Kitomer, and that’s it.

To add it by hand, the endpoint is https://mcp.kitomer.app/mcp. In Cursor’s mcp.json:

{
  "mcpServers": {
    "Kitomer": {
      "url": "https://mcp.kitomer.app/mcp"
    }
  }
}

If you belong to more than one organization, AI Connections can give you a version scoped to one, named like Kitomer for Acme, with an X-Kitomer-Org-Id header. Owners and admins see who has connected and which clients they used last.

An example

A page comes in for checkout-api. Ask your AI what happened, and it reads the incident, the place, and the logs from the same map you use:

> checkout-api just paged me. What’s going on?
get_incident          SEV1 · open 21m · paged Cy, then Ana · not acknowledged
get_node              checkout-api · Fly · acme/checkout-api · Ana Ruiz
get_place_logs        timeout acquiring connection from pool (20/20 in use)
list_similar_incidents down 19 days ago, resolved in 14m
acknowledge_incident  acknowledged · escalation stopped
add_incident_finding  evidence · fly logs

The finding appears on the incident in the portal and the iPhone app for everyone on it. When it’s over, generate_incident_write_up drafts the write-up from the timeline and findings, and seeds follow-ups from the next steps.

Every tool

Kitomer MCP 0.2.0 has 52 tools. The signed-in person’s role in the organization still applies.

GroupToolWhat it does
StatuswhoamiSigned-in user, default org, this AI client, and which accounts the org has connected.
Statuslist_connectionsGitHub, Fly, Cloudflare, Sentry, and which AI clients are using the MCP, plus companion MCPs to enable.
Statuslist_organizationsOrganizations the signed-in user belongs to.
Statusfleet_statusHeartbeat rollup across every org: up, down, and muted counts, who is on call, and down places.
Statusorg_statusHeartbeat rollup for one org, including who is on call and a slim place list.
Statuscurrent_oncallPrincipal and backup on the current shift.
Placeslist_nodesSlim place inventory: name, environment, kind, status, last beat, latency.
Placesget_nodeOne place, including the responsible person when set.
Placesget_place_logsRecent Fly stdout and stderr for a place linked to a Fly app.
Placesmatch_integrationsMatch a local git remote, fly.toml, or wrangler file to Kitomer inventory.
Placescreate_nodeCreate a place. Owners and admins.
Placesupdate_nodeUpdate a place. Owners and admins.
Varssearch_varsSearch stored env-var snapshots by key or value.
Varsget_node_vars_snapshotRead the stored vars snapshot.
Varsget_node_vars_livePull live /vars without saving them.
Varsrefresh_node_varsPull /vars and save the snapshot.
Checksget_checks_timelineHealth-check timeline for the org’s places.
Checksrun_node_checkRun a health check for one place now.
Incidentslist_incidentsOpen or recent incidents: policy pages and declared incidents.
Incidentsget_incidentOne incident plus investigation, timeline, deliveries, MTTA and MTTR, and similar past pages.
Incidentsdeclare_incidentDeclare an incident, and page on-call if you choose. SEV4 does not page.
Incidentsupdate_incidentChange summary, severity, or status. Declared incidents can be resolved here.
Incidentsacknowledge_incidentAcknowledge an open page so escalation stops.
Incidentsadd_incident_findingAppend a finding: hypothesis, evidence, next step, or similar.
Incidentsupdate_incident_findingEdit a finding.
Incidentslist_similar_incidentsPast pages on the same place.
Incidentsgenerate_incident_write_upDraft a write-up from the timeline and findings, and seed follow-ups from next steps.
Incidentsupdate_incident_write_upReplace the write-up.
Incidentsadd_incident_followupAdd a follow-up, optionally with a GitHub issue URL.
Incidentsupdate_incident_followupEdit a follow-up title, GitHub URL, or done flag.
Incidentsadd_responderAdd a responder, and page them unless told not to.
Incidentsset_commanderSet or clear the incident commander.
Incidentsmerge_incidentsFold one open incident into another. The child stops paging.
Incidentsreopen_incidentReopen a resolved incident, and page again if you choose.
Incidentscreate_maintenance_windowSilence new incidents for planned work. Checks keep running. Up to seven days.
Incidentscreate_followup_issueOpen a GitHub issue for a follow-up through the org’s GitHub App.
Incidentslist_alert_channelsRead alert destinations. URLs are masked.
Integrationslist_github_resourcesRepos visible to the org’s GitHub installation.
Integrationslist_fly_resourcesFly apps visible to Kitomer.
Integrationslist_cloudflare_resourcesCloudflare resources visible to Kitomer.
Integrationslist_sentry_resourcesSentry projects and dashboards visible to Kitomer.
On-calllist_schedulesSchedules, each with timezone, ack timeout, and escalation policy.
On-callget_scheduleOne schedule’s week: who is on call, shifts, overrides, gaps, and patterns.
On-callwho_is_on_call_atPrincipal and backup at a given moment, overrides included.
On-calllist_coverage_gapsWindows where nobody is on call.
On-callcreate_overridePut someone on call for a window. Members cover themselves; managers assign anyone.
On-calldelete_overrideRemove an override. Members remove their own; managers remove any.
On-calltake_oncallMake yourself on call from now for a few hours.
On-calllist_escalation_policiesSteps, delays, targets, severity floors, and how many times the ladder repeats.
On-callupdate_escalation_policyRename a policy, change repeats, or replace its steps. Owners and admins.
On-callupdate_alert_policyChange schedule, ack reminder, reopen window, slow trigger, or whether it pages. Owners and admins.
Coachutility_hintsWhich tools exist, example questions, and which this person has not used yet.

Companion MCPs

Kitomer knows which GitHub, Fly, Cloudflare, and Sentry accounts your organization has linked, and which repo, app, and project belong to each place. To read a vendor’s own logs or issues, your AI client also needs that vendor’s MCP. list_connections and each incident’s investigation say which ones to turn on for the session.

Try it on your own stack

Create an account, add a place or two, and connect your AI from AI Connections.

Get started