PagerDuty MCP Server

A server that exposes PagerDuty API functionality to LLMs. This server is designed to be used programmatically, with structured inputs and outputs.

Overview

The PagerDuty MCP Server provides a set of tools for interacting with the PagerDuty API. These tools are designed to be used by LLMs to perform various operations on PagerDuty resources such as incidents, services, teams, and users.

Installation

From PyPI

From Source

Requirements

• Python 3.13 or higher

• PagerDuty API key

Configuration

The PagerDuty MCP Server requires a PagerDuty API key to be set in the environment:

Usage

As Goose Extension

As Standalone Server

Response Format

All API responses follow a consistent format:

Error Handling

When an error occurs, the response will include an error object with the following structure:

Common error scenarios include:

• Invalid resource IDs (e.g., user_id, team_id, service_id)

• Missing required parameters

• Invalid parameter values

• API request failures

• Response processing errors

Parameter Validation

• All ID parameters must be valid PagerDuty resource IDs

• Date parameters must be valid ISO8601 timestamps

• List parameters (e.g., statuses, team_ids) must contain valid values

• Invalid values in list parameters will be ignored

• Required parameters cannot be None or empty strings

• For statuses in list_incidents, only triggered, acknowledged, and resolved are valid values

• For urgency in incidents, only high and low are valid values

• The limit parameter can be used to restrict the number of results returned by list operations

Rate Limiting and Pagination

• The server respects PagerDuty's rate limits

• The server automatically handles pagination for you

• The limit parameter can be used to control the number of results returned by list operations

• If no limit is specified, the server will return up to {pagerduty_mcp_server.utils.RESPONSE_LIMIT} results by default

Example Usage

User Context

Many functions accept a current_user_context parameter (defaults to True) which automatically filters results based on this context. When current_user_context is True, you cannot use certain filter parameters as they would conflict with the automatic filtering:

• For all resource types:

  • user_ids cannot be used with current_user_context=True

• For incidents:

  • team_ids and service_ids cannot be used with current_user_context=True

• For services:

  • team_ids cannot be used with current_user_context=True

• For escalation policies:

  • team_ids cannot be used with current_user_context=True

• For on-calls:

  • user_ids cannot be used with current_user_context=True

  • schedule_ids can still be used to filter by specific schedules

  • The query will show on-calls for all escalation policies associated with the current user's teams

  • This is useful for answering questions like "who is currently on-call for my team?"

  • The current user's ID is not used as a filter, so you'll see all team members who are on-call

Development

Running Tests

Note that most tests require a real connection to PagerDuty API, so you'll need to set PAGERDUTY_API_KEY in the environment before running the full test suite.

To run only unit tests (i.e. tests that don't require PAGERDUTY_API_KEY set in the environment):

To run only integration tests:

To run only parser tests:

To run only tests related to a specific submodule:

Debug Server with MCP Inspector

Contributions

Releases

This project uses Conventional Commits for automated releases. Commit messages determine version bumps:

• feat: → minor version (1.0.0 → 1.1.0)

• fix: → patch version (1.0.0 → 1.0.1)

• BREAKING CHANGE: → major version (1.0.0 → 2.0.0)

The CHANGELOG.md, GitHub releases, and PyPI packages are updated automatically.

Documentation

Tool Documentation - Detailed information about available tools including parameters, return types, and example queries

Conventions

• All API responses follow the standard format with metadata, resource list, and optional error

• Resource names in responses are always pluralized for consistency

• All functions that return a single item still return a list with one element

• Error responses include both a message and a code

• All timestamps are in ISO8601 format

• Tests are marked with pytest markers to indicate their type (unit/integration), the resource they test (incidents, teams, etc.), and whether they test parsing functionality ("parsers" marker)