PagerDuty MCP: Official Server for Incidents and On-Call
Yes — PagerDuty has an official MCP server. PagerDuty maintains it directly (PagerDuty/pagerduty-mcp-server), and you can run it yourself or point an MCP-compatible AI at PagerDuty’s own hosted version at mcp.pagerduty.com/mcp. So if you’re searching “PagerDuty MCP,” the connection you want is real and it’s first-party.
The thing worth knowing before you set it up: an MCP server hands your incident data to an AI inside a conversation you start. It’s a doorway, not a worker. Nothing watches PagerDuty for you, nothing fires when a new incident triggers, and nothing runs while the chat is closed. Here’s exactly what the PagerDuty MCP does, how to turn it on, where it stops — and what to use when you want PagerDuty work that runs on its own.
See also: the full MCP server list — which apps have one, and what each can reach.
What the PagerDuty MCP server does
Model Context Protocol (MCP) is the open standard that lets an AI client — Claude, ChatGPT, Cursor, VS Code, and others — talk to an outside app through a shared interface. PagerDuty’s official server exposes 60+ tools across incidents, services, on-call schedules, escalation policies, event orchestrations, status pages, webhooks, and analytics.
With it connected, an MCP-compatible AI client can:
- Look up and triage incidents — “what’s currently open and who’s it assigned to” answered from live PagerDuty data.
- Acknowledge, resolve, and escalate — close out a resolved incident or bump a stuck one to the next escalation level without opening the app.
- Query on-call and schedules — “who’s on call this weekend for the payments service” or create a schedule override on the spot.
- Reason across services — summarize noisy alert patterns, check a service’s dependency graph, or pull recent analytics on time-to-acknowledge.
It’s genuinely useful for ad-hoc work: ask a question about what’s happening right now, get an answer grounded in real incident data, make a change in the moment.
How to set up the PagerDuty MCP server
PagerDuty gives you two paths, both official:
- PagerDuty-hosted (fastest): in your AI client’s connector settings, add a remote MCP server pointing at
mcp.pagerduty.com/mcp(EU accounts usemcp.eu.pagerduty.com/mcp). Authenticate with a PagerDuty User API token. - Self-hosted: run the open-source server yourself via
uvxor Docker, supplying your token as thePAGERDUTY_USER_API_KEYenvironment variable, then point your MCP client (Claude Desktop, VS Code, Cursor) at the local process.
Either way, you’ll need a PagerDuty account with Advanced Permissions and a User API token — you’re granting the AI the same access your user already has. PagerDuty’s GitHub docs (pagerduty.github.io/pagerduty-mcp-server) walk through both setups in detail.
Where the PagerDuty MCP stops
None of this is a knock on MCP — it’s just the shape of the protocol. Four limits show up the moment you want more than a conversation:
- It only works inside a chat you start. Close the window and nothing happens. The AI doesn’t watch PagerDuty; it waits for you to ask.
- No triggers. A new incident firing, an escalation timing out, an on-call handoff — none of these can start anything through MCP. There’s no “when this happens in PagerDuty, do that.”
- It’s one app at a time. The PagerDuty MCP knows PagerDuty. Getting an incident’s details into Slack, a postmortem doc, and a status page update means wiring up (and authing) a separate MCP server for each, then hoping your client can juggle them in one turn.
- You own the plumbing and the scopes. The API token, its permissions, and the blast radius of an AI that can acknowledge or resolve real incidents are all on you.
So the PagerDuty MCP is a great way to ask PagerDuty things and make one-off changes. It is not a way to make PagerDuty run — to have work happen on a schedule or in reaction to an event, across the other tools an incident touches.
Running PagerDuty work that doesn’t need a chat open
That “run on its own, across apps” gap is exactly where Carly fits. Carly connects to PagerDuty natively — no MCP server to host, no API token to manage — and to the ~260 other apps it supports, plus anything with a public API through your own key. The difference from MCP is the important part: Carly’s workflows are triggered and scheduled, so PagerDuty work happens whether or not anyone has a chat window open.
A few things that MCP can’t do but a Carly workflow can:
- When a Sev-1 incident triggers → post the details to the on-call Slack channel, open a Zoom bridge, and start drafting the incident summary — automatically, the moment it happens.
- Every Monday morning → pull last week’s incidents, summarize mean time to acknowledge and resolve, and email the report to the engineering lead.
- When an incident resolves → draft a postmortem outline from the timeline, log it in the team’s doc tool, and notify the service owner for review.
The non-AI steps — the moving, matching, and routing between apps — are free and unlimited, the Zapier-style backbone of the workflow. The AI steps (drafting, summarizing, deciding) start at $35/month. You describe the outcome in plain language and Carly wires up the PagerDuty connection and everything downstream.
If you just want to interrogate your incidents from a chat, PagerDuty’s official MCP server is the right tool and it’s free to connect. If you want PagerDuty to actually do things — on a trigger, on a schedule, across every tool an incident flows through — that’s the job MCP wasn’t built for, and it’s the one Carly was.
FAQ
Does PagerDuty have an official MCP server?
Yes. PagerDuty maintains its own server (PagerDuty/pagerduty-mcp-server), available either as a PagerDuty-hosted remote server at mcp.pagerduty.com/mcp or as a self-hosted open-source server you run yourself.
Is the PagerDuty MCP server free? Connecting to it is free — you’re authorizing an AI client with your existing PagerDuty User API token and permissions. You still need a PagerDuty plan with Advanced Permissions for the account the token belongs to.
Can the PagerDuty MCP trigger automations? No. MCP is request/response inside an AI chat — it has no triggers and nothing runs when the conversation is closed. For event- or schedule-driven PagerDuty work across apps, you need a workflow tool like Carly rather than an MCP server.
What AI tools can connect to PagerDuty over MCP? Any MCP-compatible client — Claude Desktop, VS Code, Cursor, and others — can connect to the PagerDuty MCP server, whether you use PagerDuty’s hosted version or run it yourself.
Can I connect PagerDuty to AI without coding or hosting a server? Yes. You don’t have to touch MCP at all. Carly connects to PagerDuty for you and lets you build the automation in plain language — describe what you want to happen and it wires up PagerDuty and the other apps involved, with no server to host and no code to write.
Ready to automate your busywork?
Carly schedules, researches, and briefs you—so you can focus on what matters.
See what people say
"Before Carly, I relied on a Calendly link, but the whole process felt impersonal and not very professional. Carly changed that by handling all the back-and-forth, so I'm no longer stuck in endless email threads trying to line up schedules.
Now Carly reaches out to candidates, shares my real-time availability, lets them pick a slot, then sends a Zoom link and drops it straight into my calendar. She sends reminders to both of us before each call, which has significantly reduced no-shows and last-minute confusion.
On top of scheduling, Carly acts like a full executive assistant, sending me my schedule the night before so I can prepare for each call. It reminds me of the old x.ai assistant, but Carly is noticeably smarter, faster, and better suited to my healthcare recruitment business."
