How is this different from connecting PagerDuty MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the PagerDuty MCP API changes?

We track the PagerDuty MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different PagerDuty tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in PagerDuty?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the PagerDuty MCP server myself?

No. TrustGate connects to the PagerDuty MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to PagerDuty directly.

Connect PagerDuty MCP to your AI agents, securely.

Q: Is PagerDuty MCP secure?

The server itself exposes 18 tools, and some of them can write to your PagerDuty account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches PagerDuty.

One secured endpoint for every PagerDuty call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try PagerDuty MCP now

What your agents can ask once PagerDuty MCP is connected.

Select the tools your AI agents can call

18 tools from the PagerDuty MCP schema.

Showing 18 tools

manage_incidentswriteManages one or more incidents by changing status, urgency, assignment or escalation level.
browse_incidentsreadLists and gets incidents, their alerts and notes, related, past and outlier incident context, change events and incident workflows.
browse_servicesreadLists services and gets the details of a specific service.
manage_serviceswriteCreates and updates services.
browse_schedulesreadLists and gets schedules, the users on a schedule and current on-call entries.
manage_scheduleswriteCreates and updates schedules and creates schedule overrides that change who is on call.
browse_teamsreadLists teams, gets team details and lists team members.
manage_teamshigh riskCreates, updates and deletes teams and adds or removes team members.
browse_usersreadLists users and gets the details of a specific user.
browse_escalation_policiesreadLists escalation policies and gets the details of a specific policy.
browse_alert_groupingreadLists alert grouping settings and gets the details of a specific setting.
manage_alert_groupinghigh riskCreates, updates and deletes alert grouping settings.
browse_event_orchestrationsreadLists and gets event orchestrations, including their router, service and global rules.
manage_event_orchestrationswriteUpdates an event orchestration router and appends routing rules.
browse_status_pagesreadLists status pages with their severities, impacts and statuses, and gets status page posts and post updates.
manage_status_pageswriteCreates status page posts and post updates.
browse_change_eventsreadLists and gets change events, including the change events of a service.
browse_activityreadLists and gets log entries recording activity in the account.

What PagerDuty MCP exposes

PagerDuty MCP groups its 18 tools into 9 categories, each with a suggested starting policy.

All 18 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Incidents	Incident listing, details, notes, status changes, assignment and escalation	Read / Write	Require approval before resolving or reassigning incidents
On-Call	On-call entries, schedules and schedule overrides	Read / Write	Audit roster changes
Services	Service listing, details, creation and updates	Read / Write	Approve service configuration changes
Escalation Policies	Escalation policy listing and details	Read	Allow read-only access
Teams & Users	Teams, team membership and users in the account	Read / Write	Limit organization access
Alert Grouping	Alert grouping settings: listing, details, creation, updates and deletion	Read / Write	Approve grouping changes; they affect alert noise
Event Orchestration	Event orchestrations: router, service and global rules, router updates and new routing rules	Read / Write	Approve routing rule changes; they decide where events and alerts go
Status Pages	Status pages, severities, impacts, statuses, posts and post updates	Read / Write	Require approval before creating posts; they are visible to your status page audience
Change Events & Activity	Change events and account log entries	Read	Allow read-only access for investigations

Connect PagerDuty MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect PagerDuty
Find PagerDuty in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow PagerDuty MCP or block it. You allow the exact tools each agent can call, one by one.

PagerDuty MCP	18 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 18 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is PagerDuty MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	PagerDuty MCP18 documented tools. Each tool on the PagerDuty-hosted server groups several actions.
Coding assistants	Connection & credentialsper user	Teams & Users3 tools
Internal copilots	Tool access policiesdeny by default	Incidents2 tools
Workflow automations	Request & response inspectioninline	On-Call2 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools11 tools