NewCost control: a token allowance a month for each model choice — when one runs out, the cheaper one answers.See how it works
memtro
MCP server · Engineering and operations

PagerDuty MCP server

PagerDuty in any MCP client, through Memtro: PagerDuty does not publish this server. Memtro's PagerDuty connector reads PagerDuty through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.

What the model can do

Search incidents by status, urgency, service, team and time, read an incident's timeline and notes, see who is on call now or in a window, and look up services, escalation policies, users and teams; can also acknowledge, resolve, reassign, escalate, snooze or annotate an incident, raise one, and schedule a maintenance window so planned work on a service raises no incidents, when you ask.

Reads

  • pagerduty_incidentsSearch PagerDuty incidents by status (open = triggered + acknowledged, default), urgency, service, team, time window and title text, newest first.
  • pagerduty_incidentOne incident by id (P…) or incident number with its description, assignees and the timeline from its log entries (trigger details, acknowledgements…
  • pagerduty_oncallWho is on call: right now by default, or within a time window, optionally for one escalation policy, schedule or user (names or ids).
  • pagerduty_servicesPagerDuty services (what incidents are opened against), optionally filtered by name or team, with status, escalation policy…
  • pagerduty_peopleUsers (name, email, role, job title, time zone, teams) and teams in the PagerDuty account, optionally filtered by name or restricted to one team.

Acts, when you ask

These change something in PagerDuty. 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.

  • pagerduty_update_incidentChanges a PagerDuty incident — acknowledges it, resolves it, reassigns it, escalates it to a higher level of its escalation policy…
  • pagerduty_add_noteAdds a note to a PagerDuty incident, which everybody on it sees in its timeline.
  • pagerduty_create_incidentRaises a PagerDuty incident on a service.
  • pagerduty_maintenance_windowTakes one or more PagerDuty services out of service for a window of planned work — while it is open those services raise no incidents at all…

Connect it

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

Claude Code

One command registers the server; the tools are then available in every session.

claude mcp add --transport http memtro https://platform.memtro.com/api/mcp \
  --header "Authorization: Bearer sk-memtro-..."

Cursor

Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.

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

Claude Desktop

Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…

OpenCode

A remote server in opencode.json.

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

Any other client

Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.

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 PagerDuty 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

  • › What incidents are open right now and who is working them?
  • › Who is on call for the payments escalation policy tonight?
  • › How long did incident 4821 take to resolve and who resolved it?
  • › Which services had high-urgency incidents this month?
  • › Show the timeline of the database outage last Tuesday

Questions

Is this an official PagerDuty MCP server?
No. It is Memtro's MCP server with Memtro's PagerDuty connector behind it: the connector reads PagerDuty through its API with the credentials you connect on Dashboard → Connections, and PagerDuty 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 PagerDuty?
Only when you ask, and only what it has been granted: acknowledge, resolve, reassign, reprioritise, escalate or snooze an incident; add a note to an incident; raise an incident on a service, which pages whoever is on call; schedule a maintenance window so planned work raises no incidents, or end one early. 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