Connect
Optimize
Secure
PagerDuty MCP Server
for AI Agents
Production-ready PagerDuty MCP server with 38 extensible actions — plus built-in authentication, security, and optimized execution.
PagerDuty MCP Server
Built by 
StackOne
StackOne 
Coverage
38 Agent Actions
Create, read, update, and delete across PagerDuty — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your PagerDuty MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every PagerDuty tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every PagerDuty call.
Tools Discovery →What is the PagerDuty MCP Server?
A PagerDuty MCP server lets AI agents read and write PagerDuty data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's PagerDuty MCP server ships with 38 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All PagerDuty MCP Tools and Actions
Every action from PagerDuty's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Incidents
- Create Incident
Manually create a new incident through the API with specified title, service, and urgency.
- List Incidents
Retrieve a paginated list of incidents with filtering options by status, urgency, time range, service, or team.
- Get Incident
Retrieve detailed information about a specific incident including timeline, responders, alerts, and notes.
- Update Incident
Modify incident properties including title, service, urgency, priority, assignments, escalation policy, conference bridge, status, escalation level, and resolution to comprehensively update incident details.
Services
- Create Service
Create a new service with escalation policy and settings to automate service provisioning during infrastructure deployment.
- List Services
Retrieve all services in the account with filtering options to populate service directories, build catalogs, and audit configurations.
- Get Service
Fetch detailed configuration and metadata for a specific service including settings, integrations, and escalation policies.
- Update Service
Modify service configuration, settings, or associations to update properties, change escalation policies, or enable features.
- Delete Service
Remove a service from the account to clean up deprecated services during decommissioning.
Users
- Create User
Add a new user to the account to automate user onboarding from HR systems or identity providers.
- List Users
Retrieve all users in the account with filtering options to sync with HR systems, generate reports, and audit access.
- Get User
Fetch detailed information about a specific user including contact methods, notification rules, and roles.
- Update User
Modify user properties, roles, or settings to update information, change roles, or modify notification preferences.
- Delete User
Remove a user from the account to automate user offboarding during employee departures.
Teams
- Create Team
Create a new team to organize users and services by team structure within the organization.
- List Teams
Retrieve all teams in the account to organize users and services by team structure.
- Get Team
Fetch detailed team information including members to retrieve team composition and associated resources.
- Update Team
Modify team properties including name, description, or default role to update team structure.
- Delete Team
Remove a team from the account to clean up unused teams during organizational restructuring.
Schedules
- Create Schedule
Create a new on-call schedule with rotation layers to automate schedule creation during team onboarding.
- List Schedules
Retrieve all on-call schedules in the account to display rotations and audit schedule coverage.
- Get Schedule
Fetch detailed schedule information including layers and overrides to retrieve full configuration for analysis or cloning.
- Delete Schedule
Remove a schedule from the account to clean up unused schedules during reorganization.
Incident Types
- List Incident Types
List available incident types
- Get Incident Type
Get detailed information about a single incident type
Vendors
- List Vendors
Retrieve available integration vendors and types to discover supported monitoring tools and integration options.
- Get Vendor
Fetch detailed information about a specific vendor including integration capabilities and configuration options.
Other (11)
- Add Note To Incident
Add contextual notes or comments to an incident to document investigation findings, remediation steps, or team communication.
- List Incident Notes
Retrieve all notes associated with an incident for extracting communication history during postmortems or analysis.
- List Incident Log Entries
Retrieve the complete timeline of actions and changes for an incident to audit handling, generate reports, and analyze response patterns.
- List Escalation Policies
List all existing escalation policies
- Get Escalation Policy
Get information about an existing escalation policy
- List On-Calls
Query who is currently on-call across schedules and escalation policies to display current information in dashboards or chat bots.
- List Priorities
Retrieve all incident priorities ordered by severity from most to least severe to populate priority dropdowns and validate priority selections during incident creation.
- List Licenses
Retrieve all licenses available in the account to monitor license types and availability.
- List License Allocations
Retrieve all user license allocations to monitor license usage and identify unassigned licenses.
- Get User License
Retrieve the license allocated to a specific user to verify license assignment and type.
- List Audit Records
Retrieve audit trail of configuration changes and actions to track compliance, investigate changes, and perform security audits.
Set Up Your PagerDuty MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to PagerDuty in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}PagerDuty MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
PagerDuty MCP Server FAQ
PagerDuty MCP server vs direct API integration — what's the difference?
A PagerDuty MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling PagerDuty. A PagerDuty MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling PagerDuty at runtime. StackOne provides both.
How does PagerDuty authentication work for AI agents?
PagerDuty authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own PagerDuty account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are PagerDuty MCP tools vulnerable to prompt injection?
Yes — PagerDuty MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a PagerDuty agent and how do I avoid it?
Context bloat happens when PagerDuty tool schemas and API responses eat your PagerDuty agent's memory, preventing it from reasoning effectively. A single PagerDuty query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my PagerDuty agent can access?
Yes — you can limit which actions your PagerDuty agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my PagerDuty MCP server?
Yes — you can create custom agent actions for your PagerDuty MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research PagerDuty's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a PagerDuty MCP server?
Skip a PagerDuty MCP server if your integration is purely software-to-software — direct PagerDuty API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call PagerDuty actions at runtime.
What AI frameworks and AI clients does the StackOne PagerDuty MCP server support?
The StackOne PagerDuty MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.