PagerDuty's official MCP Server

PagerDuty's local MCP (Model Context Protocol) server which provides tools to interact with your PagerDuty account, allowing you to manage incidents, services, schedules, event orchestrations, and more directly from your MCP-enabled client.

Embedded MCP Apps (Developer Experience)

Interactive React UIs for PagerDuty incident management, embedded directly in the Python MCP server for seamless IDE integration. Manage your full incident lifecycle without leaving your IDE.

Available Apps:

1. Incident Command Center 🚨

Full incident lifecycle management from your IDE:

• Real-time incident feed with auto-refresh
• Deep incident details: timeline, notes, alerts, changes
• Quick actions: acknowledge, resolve, escalate
• AI-powered similar incident detection
• Alert inspection with raw data

Usage in VS Code: Ask Claude: Show me the incident command center

2. On-Call Manager 📅

Schedule management with override CRUD and coverage wizards:

• View current on-call rotations across schedules
• Create, edit, and delete schedule overrides
• Escalation policy management with modal-based UI

Usage in VS Code: Ask Claude: Show me the on-call manager

3. On-Call Compensation Report 💰

Per-user on-call metrics with compliance tracking:

• Hours worked, incident counts, interruption rates
• Business hours vs. off-hours breakdown
• Compliance status with EU Working Time Directive limits
• Fairness/equity scoring across responders
• CSV export

Usage in VS Code: Ask Claude: Show me the oncall compensation report

4. Service Dependency Graph 🕸️

Interactive graph of service relationships and dependencies:

• Directed graph visualization
• Impact sidebar showing upstream/downstream services

Usage in VS Code: Ask Claude: Show me the service dependency graph

5. Onboarding Wizard 🧙

Step-by-step PagerDuty account setup:

• Team creation and user onboarding
• Schedule setup with timezone support
• Escalation policy and service configuration
• AIOps / alert grouping configuration
• Incident workflow setup

Usage in VS Code: Ask Claude: Open the onboarding wizard

Architecture:

• ✅ Native VS Code integration (MCP resources)
• ✅ Single process, no HTTP server management
• ✅ Direct access to all PagerDuty MCP tools
• ✅ Simple deployment: uv run pagerduty-mcp

Prerequisites

• asdf-vm installed.

• uv installed globally.

• A PagerDuty User API Token. To obtain a PagerDuty User API Token, follow these steps:

  1. Navigate to User Settings. Click on your user profile icon, then select My Profile and then User Settings.

     For Freemium accounts, the permissions for generating User API tokens are limited to the user role as defined here.

  2. In your user settings, locate the API Access section.
  3. Click the Create API User Token button and follow the prompts to generate a new token.
  4. Copy the generated token and store it securely. You will need this token to configure the MCP server.

  Use of the PagerDuty User API Token is subject to the PagerDuty Developer Agreement.

Using with MCP Clients

Cursor Integration

You can configure this MCP server directly within Cursor's settings.json file, by following these steps:

1. Open Cursor settings (Cursor Settings > Tools > Add MCP, or Cmd+, on Mac, or Ctrl+, on Windows/Linux).

2. Add the following configuration:

   json

   {
     "mcpServers": {
       "pagerduty-mcp": {
         "type": "stdio",
         "command": "uvx",
         "args": [
           "pagerduty-mcp",
           "--enable-write-tools"
           // This flag enables write operations on the MCP Server enabling you to creating incidents, schedule overrides and much more
         ],
         "env": {
           "PAGERDUTY_USER_API_KEY": "${input:pagerduty-api-key}"
         }
       }
     }
   }
   

VS Code Integration

You can configure this MCP server directly within Visual Studio Code's settings.json file, allowing VS Code to manage the server lifecycle.

1. Open VS Code settings (File > Preferences > Settings, or Cmd+, on Mac, or Ctrl+, on Windows/Linux).

2. Search for "mcp" and ensure "Mcp: Enabled" is checked under Features > Chat.

3. Click "Edit in settings.json" under "Mcp > Discovery: Servers".

4. Add the following configuration:

   json

   {
       "mcp": {
           "inputs": [
               {
                   "type": "promptString",
                   "id": "pagerduty-api-key",
                   "description": "PagerDuty API Key",
                   "password": true
               }
           ],
           "servers": {
               "pagerduty-mcp": { 
                   "type": "stdio",
                   "command": "uvx",
                   "args": [
                       "pagerduty-mcp",
                       "--enable-write-tools"
                       // This flag enables write operations on the MCP Server enabling you to creating incidents, schedule overrides and much more
                   ],
                   "env": {
                       "PAGERDUTY_USER_API_KEY": "${input:pagerduty-api-key}",
                       "PAGERDUTY_API_HOST": "https://api.pagerduty.com"
                       // If your PagerDuty account is located in EU update your API host to https://api.eu.pagerduty.com
                   }
               }
           }
       }
   }
   

Trying it in VS Code Chat (Agent)

1. Ensure MCP is enabled in VS Code settings (Features > Chat > "Mcp: Enabled").
2. Configure the server as described above.
3. Open the Chat view in VS Code (View > Chat).
4. Make sure Agent mode is selected. In the Chat view, you can enable or disable specific tools by clicking the 🛠️ icon.
5. Enter a command such as Show me the latest incident or List my event orchestrations to interact with your PagerDuty account through the MCP server.
6. You can start, stop, and manage your MCP servers using the command palette (Cmd+Shift+P/Ctrl+Shift+P) and searching for MCP: List Servers. Ensure the server is running before sending commands. You can also try to restart the server if you encounter any issues.

Claude Desktop Integration

You can configure this MCP server to work with Claude Desktop by adding it to Claude's configuration file.

1. Locate your Claude Desktop configuration file:

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

2. Create or edit the configuration file and add the following configuration:

   json

   {
     "mcpServers": {
       "pagerduty-mcp": {
         "command": "uvx",
         "args": [
           "pagerduty-mcp",
           "--enable-write-tools"
         ],
         "env": {
           "PAGERDUTY_USER_API_KEY": "your-pagerduty-api-key-here",
           "PAGERDUTY_API_HOST": "https://api.pagerduty.com"
         }
       }
     }
   }
   

3. Replace the placeholder values:

   • Replace /path/to/your/mcp-server-directory with the full path to the directory where you cloned the MCP server (e.g., /Users/yourname/code/pagerduty-mcp)
   • Replace your-pagerduty-api-key-here with your actual PagerDuty User API Token
   • If your PagerDuty account is located in the EU, update the API host to https://api.eu.pagerduty.com

4. Restart Claude Desktop completely for the changes to take effect.

5. Test the integration by starting a conversation with Claude and asking something like "Show me my latest PagerDuty incidents" or "List my event orchestrations" to verify the MCP server is working.

   Security Note: Unlike VS Code's secure input prompts, Claude Desktop requires you to store your API key directly in the configuration file. Ensure this file has appropriate permissions (readable only by your user account) and consider the security implications of storing credentials in plain text.

Running with Docker

The PagerDuty MCP server can be run in a Docker container, providing an isolated and portable deployment option. The Docker image uses stdio transport for MCP communication.

Prerequisites

• Docker installed
• A PagerDuty User API Token (see Prerequisites)

Quick Start

Build the Docker image:

docker build -t pagerduty-mcp:latest .

Run in read-only mode (default):

docker run -i --rm \
  -e PAGERDUTY_USER_API_KEY="your-api-key-here" \
  pagerduty-mcp:latest

Run with write tools enabled:

docker run -i --rm \
  -e PAGERDUTY_USER_API_KEY="your-api-key-here" \
  pagerduty-mcp:latest --enable-write-tools

For EU region:

docker run -i --rm \
  -e PAGERDUTY_USER_API_KEY="your-api-key-here" \
  -e PAGERDUTY_API_HOST="https://api.eu.pagerduty.com" \
  pagerduty-mcp:latest

Using with MCP Clients via Docker

To integrate the Docker container with MCP clients, you can use Docker as the command:

Claude Desktop example:

{
  "mcpServers": {
    "pagerduty-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "PAGERDUTY_USER_API_KEY=your-api-key-here",
        "pagerduty-mcp:latest"
      ]
    }
  }
}

Note: The Docker container uses stdio transport, making it compatible with MCP clients that expect standard input/output communication. Ensure you build the image first using docker build -t pagerduty-mcp:latest .

Transport modes

The server supports three MCP transports, selected via the --transport flag:

For HTTP-based transports, --host (default 127.0.0.1) and --port (default 8000) control the listen address. These can also be set via environment variables MCP_HOST and MCP_PORT. Note: MCP_PORT must always be a valid integer — the CLI parses its type at startup regardless of --transport; range validation (1–65535) only applies for HTTP transports.

⚠️ Security — HTTP transports have no built-in authentication. When running streamable-http or sse, the MCP endpoint is exposed with no authentication, and every request uses the single PAGERDUTY_USER_API_KEY the server was started with. Any client that can reach the host/port can invoke tools — including write tools when --enable-write-tools is set — with that key's full PagerDuty privileges.

• The default bind address is 127.0.0.1 (loopback only) — keep it that way for local use.
• Only bind to 0.0.0.0/a routable address when the endpoint sits behind an authenticating reverse proxy / API gateway (e.g. oauth2-proxy, mTLS) or on a trusted network. Do not expose it directly to untrusted networks.

Example: run as a remote streamable-HTTP server

pagerduty-mcp --transport streamable-http --host 0.0.0.0 --port 8000
# MCP endpoint: http://<your-machine-ip>:8000/mcp
# ⚠️ Only use --host 0.0.0.0 behind an authenticating proxy or on a trusted network.

Using environment variables:

MCP_HOST=0.0.0.0 MCP_PORT=8000 pagerduty-mcp --transport streamable-http
# ⚠️ Only use MCP_HOST=0.0.0.0 behind an authenticating proxy or on a trusted network.

Docker:

docker run -d -p 8000:8000 \
  -e PAGERDUTY_USER_API_KEY="your-api-key-here" \
  -e MCP_HOST=0.0.0.0 \
  -e MCP_PORT=8000 \
  pagerduty-mcp:latest \
  --transport streamable-http
# ⚠️ Only use MCP_HOST=0.0.0.0 behind an authenticating proxy or on a trusted network.

The default remains stdio so existing local integrations are unaffected.

Set up locally

1. Clone the repository

2. Install asdf plugins

   shell

   asdf plugin add python
   asdf plugin add nodejs https://github.com/asdf-vm/asdf-nodejs.git
   asdf plugin add uv
   

3. Install tool versions using asdf:

   shell

   asdf install
   

4. Create a virtual environment and install dependencies using uv (now that asdf has set the correct Python and uv versions):

   shell

   uv sync
   

5. Ensure uv is available globally.

   The MCP server can be run from different places so you need uv to be available globally. To do so, follow the official documentation.

   Tip: You may need to restart your terminal and/or VS Code for the changes to take effect.

6. Run it locally

   To run your cloned PagerDuty MCP Server you need to update your configuration to use uv instead of uvx.

   json

   "pagerduty-mcp": { 
       "type": "stdio",
       "command": "uv",
       "args": [
           "run",
           "--directory",
           "/path/to/your/mcp-server-directory",
           // Replace with the full path to the directory where you cloned the MCP server, e.g. "/Users/yourname/code/mcp-server",     
           "python",
           "-m",
           "pagerduty_mcp",
           "--enable-write-tools"
           // This flag enables write operations on the MCP Server enabling you to creating incidents, schedule overrides and much more
       ],
       "env": {
           "PAGERDUTY_USER_API_KEY": "${input:pagerduty-api-key}",
           "PAGERDUTY_API_HOST": "https://api.pagerduty.com"
           // If your PagerDuty account is located in EU update your API host to https://api.eu.pagerduty.com
       }
   }
   

Configuration

The MCP server is configured via environment variables:

Available Tools and Resources

This section describes the tools provided by the PagerDuty MCP server. They are categorized based on whether they only read data or can modify data in your PagerDuty account.

Important: By default, the MCP server only exposes read-only tools. To enable tools that can modify your PagerDuty account (write-mode tools), you must explicitly start the server with the --enable-write-tools flag. This helps prevent accidental changes to your PagerDuty data.

Support

PagerDuty's MCP server is an open-source project, and as such, we offer only community-based support. If assistance is required, please open an issue in GitHub or PagerDuty's community forum.

Contributing

If you are interested in contributing to this project, please refer to our Contributing Guidelines.