PagerDuty MCP Server
by wpfleger96
A server that exposes PagerDuty API functionality to LLMs. This server is designed to be used programmatically, with structured inputs and outputs.
Last updated: N/A
What is PagerDuty MCP Server?
The PagerDuty MCP Server provides a set of tools for interacting with the PagerDuty API, enabling LLMs to perform various operations on PagerDuty resources such as incidents, services, teams, and users.
How to use PagerDuty MCP Server?
The server can be installed from PyPI or from source. It requires a PagerDuty API key to be set as an environment variable. It can be used as a Goose extension or as a standalone server, with API requests and responses following a defined JSON format.
Key features of PagerDuty MCP Server
Exposes PagerDuty API functionality
Designed for LLM integration
Structured inputs and outputs
Automatic pagination handling
Error handling with detailed messages and codes
Parameter validation
Respects PagerDuty's rate limits
Use cases of PagerDuty MCP Server
Listing incidents based on various criteria (status, service, team, date range)
Retrieving information about PagerDuty resources (incidents, services, teams, users)
Automating PagerDuty operations through LLMs
Integrating PagerDuty with other systems
Filtering results based on the current user's context
FAQ from PagerDuty MCP Server
What is the required Python version?
What is the required Python version?
Python 3.13 or higher is required.
How do I configure the server?
How do I configure the server?
You need to set the PAGERDUTY_API_KEY environment variable with your PagerDuty API key.
What is the format of API responses?
What is the format of API responses?
All API responses follow a consistent JSON format with metadata, a resource list (pluralized), and an optional error object.
How does the server handle rate limiting?
How does the server handle rate limiting?
The server respects PagerDuty's rate limits and automatically handles pagination.
What are some common error scenarios?
What are some common error scenarios?
Common error scenarios include invalid resource IDs, missing required parameters, invalid parameter values, API request failures, and response processing errors.