PagerDuty MCP server for AI agents

The PagerDuty MCP Server provides a programmatic interface for LLMs to interact with PagerDuty's API functionality, enabling operations on incidents, services, teams, and users with structured inputs and outputs.

Installation

Prerequisites

Before installing the PagerDuty MCP Server, you'll need:

Python installed on your system
A valid PagerDuty API token

Installation Steps

Initialize your local Python environment:

cd pagerduty-mcp-server
brew install uv
uv sync

Set up your PagerDuty API token in your environment:

export PAGERDUTY_API_TOKEN=your_api_token_here

Usage

You can use the PagerDuty MCP Server either as a Goose extension or as a standalone server.

Using as a Goose Extension

In Goose, navigate to Settings > Extensions > Add
Set Type to StandardIO
Enter the absolute path to the project's CLI:

uv run /path/to/mcp/pagerduty-mcp-server/.venv/bin/pagerduty-mcp-server

Enable the extension and verify that Goose recognizes your tools

Running as a Standalone Server

To run the server independently:

uv run path/to/repo/pagerduty-mcp-server/.venv/bin/pagerduty-mcp-server

Response Format

All API responses follow this consistent structure:

{
  "metadata": {
    "count": 5,
    "description": "A short summary of the results"
  },
  "resources": [
    {
      "id": "example_id",
      "name": "example_name",
      "other_properties": "..."
    }
  ],
  "error": {
    "message": "Human-readable error description",
    "code": "MACHINE_READABLE_ERROR_CODE"
  }
}

The error object will only be present if an error occurred during processing.

Error Handling

When errors occur, the response includes an error object:

{
  "metadata": {
    "count": 0,
    "description": "Error occurred while processing request"
  },
  "error": {
    "message": "Invalid user ID provided",
    "code": "INVALID_USER_ID"
  }
}

Common error scenarios include invalid resource IDs, missing parameters, invalid parameter values, API failures, and response processing errors.

Parameter Validation

All ID parameters must be valid PagerDuty resource IDs
Date parameters must be ISO8601 timestamps
List parameters must contain valid values
Required parameters cannot be None or empty strings
For incident statuses, only triggered, acknowledged, and resolved are valid
For incident urgency, only high and low are valid
The limit parameter restricts the number of results returned

Rate Limiting and Pagination

The server respects PagerDuty's rate limits
Pagination is handled automatically
The limit parameter controls the number of results returned

User Context

Many functions accept a current_user_context parameter (defaults to True), which filters results based on the current user. When this is enabled, certain filter parameters cannot be used:

For all resources: 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

This feature is useful for queries like "who is currently on-call for my team?"

Example Queries

The PagerDuty MCP Server can be used to answer queries such as:

Are there any incidents assigned to me currently in PagerDuty?
Do I have any upcoming on-call schedule in the next 2 weeks?
Who else is a member of the personalization team?

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "pagerduty-mcp-server" '{"command":"uv","args":["run","pagerduty-mcp-server"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "pagerduty-mcp-server": {
            "command": "uv",
            "args": [
                "run",
                "pagerduty-mcp-server"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "pagerduty-mcp-server": {
            "command": "uv",
            "args": [
                "run",
                "pagerduty-mcp-server"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect