PagerDuty

PagerDuty MCP Server for LLM Agent Integration
  • python

7

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "wpfleger96-pagerduty-mcp-server": {
      "command": "uvx",
      "args": [
        "pagerduty-mcp-server"
      ],
      "env": {
        "PAGERDUTY_API_TOKEN": "<PAGERDUTY_API_TOKEN>"
      }
    }
  }
}

The PagerDuty MCP Server exposes PagerDuty API functionality to large language models, enabling structured interactions with incidents, services, teams, and users. It is designed to be used programmatically, with well-defined inputs and outputs to integrate PagerDuty capabilities into automated workflows.

How to use

You can run this MCP server locally and connect to it from your MCP client or orchestration layer. Use a stdio configuration to launch the server as a local process, or run it as a standalone server if you prefer a direct command invocation. Each configured entry provides a ready-to-use command that you can paste into your environment or automation scripts.

How to install

Prerequisites: you need Python-based code for the MCP server and a runner to execute the MCP process. Ensure these tools are available in your environment.

cd pagerduty-mcp-server
brew install uv
uv sync

Set your PagerDuty API token in one of the supported ways.

Option 1: Environment variable

export PAGERDUTY_API_TOKEN=your_api_token_here

Option 2: .env file (recommended)

echo "PAGERDUTY_API_TOKEN=your_api_token_here" > .env

The server will automatically load environment variables from the .env file if present.

## Configuration and running tips

There are multiple ways to connect to the PagerDuty MCP Server depending on your environment. The following stdio configurations are provided to run the server locally from different contexts.
Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational