Skip to main content
Glama
pagerduty-mcp-community

pagerduty-mcp-community

by carlyou

PagerDuty MCP Server - Community Edition

About This Fork

This is a community-maintained fork of PagerDuty's official MCP Server with additional capabilities and features. The enhancements in this fork have been submitted as a pull request to the upstream repository but have not yet been merged.

Key differences from the official package:

  • Additional tools and functionality (see capabilities below)

  • Community-driven development and faster iteration

  • Published on PyPI as pagerduty-mcp-community for easy installation

For the official PagerDuty package, see pagerduty-mcp on PyPI.

Related MCP server: MCP Setup Server

Overview

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.

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.

    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:

    {
      "mcpServers": {
        "pagerduty-mcp": {
          "type": "stdio",
          "command": "uvx",
          "args": [
            "pagerduty-mcp-community",
            "--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:

    {
        "mcp": {
            "inputs": [
                {
                    "type": "promptString",
                    "id": "pagerduty-api-key",
                    "description": "PagerDuty API Key",
                    "password": true
                }
            ],
            "servers": {
                "pagerduty-mcp": {
                    "type": "stdio",
                    "command": "uvx",
                    "args": [
                        "pagerduty-mcp-community",
                        "--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:

    {
      "mcpServers": {
        "pagerduty-mcp": {
          "command": "uvx",
          "args": [
            "pagerduty-mcp-community",
            "--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.

Set up locally

  1. Clone the repository

  2. Install asdf plugins

    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:

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

    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.

    "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
        }
    }

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.

Tool

Area

Description

Read-only

create_alert_grouping_setting

Alert Grouping

Creates a new alert grouping setting

❌

delete_alert_grouping_setting

Alert Grouping

Deletes an alert grouping setting

❌

get_alert_grouping_setting

Alert Grouping

Retrieves a specific alert grouping setting

✅

list_alert_grouping_settings

Alert Grouping

Lists alert grouping settings with filtering

✅

update_alert_grouping_setting

Alert Grouping

Updates an existing alert grouping setting

❌

get_event_orchestration

Event Orchestrations

Retrieves a specific event orchestration

✅

get_event_orchestration_router

Event Orchestrations

Gets the router configuration for an event orchestration

✅

list_event_orchestrations

Event Orchestrations

Lists event orchestrations with optional filtering

✅

update_event_orchestration_router

Event Orchestrations

Updates the router configuration for an event orchestration

❌

append_event_orchestration_router_rule

Event Orchestrations

Adds a new routing rule to an event orchestration router

❌

list_escalation_policies

Escalation Policy

Lists escalation policies

✅

get_escalation_policy

Escalation Policy

Retrieves a specific escalation policy

✅

add_note_to_incident

Incidents

Adds note to an incident

❌

add_responders

Incidents

Adds responders to an incident

❌

create_incident

Incidents

Creates a new incident

❌

get_incident

Incidents

Retrieves a specific incident

✅

list_incidents

Incidents

Lists incidents

✅

manage_incidents

Incidents

Updates status, urgency, assignment, or escalation level

❌

add_team_member

Teams

Adds a user to a team with a specific role

❌

create_team

Teams

Creates a new team

❌

delete_team

Teams

Deletes a team

❌

get_team

Teams

Retrieves a specific team

✅

list_team_members

Teams

Lists members of a team

✅

list_teams

Teams

Lists teams

✅

remove_team_member

Teams

Removes a user from a team

❌

update_team

Teams

Updates an existing team

❌

get_user_data

Users

Gets the current user's data

✅

list_users

Users

Lists users in the PagerDuty account

✅

list_oncalls

On-call

Lists on-call schedules

✅

create_schedule_override

Schedules

Creates an override for a schedule

❌

get_schedule

Schedules

Retrieves a specific schedule

✅

list_schedule_users

Schedules

Lists users in a schedule

✅

list_schedules

Schedules

Lists schedules

✅

create_service

Services

Creates a new service

❌

get_service

Services

Retrieves a specific service

✅

list_services

Services

Lists services

✅

update_service

Services

Updates an existing service

❌

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.

Available Tools

20 tools
get_alert_grouping_settingB
Read-onlyIdempotent

Get details for a specific alert grouping setting.

Args:
    setting_id: The ID of the alert grouping setting to retrieve

Returns:
    Alert grouping setting details

Inputs: setting_id (required). Returns: Defines how alerts will be automatically grouped into incidents based on the co…

get_escalation_policyB
Read-onlyIdempotent

Get a specific escalation policy.

Args:
    policy_id: The ID of the escalation policy to retrieve

Returns:
    Escalation policy details

Inputs: policy_id (required). Returns: id, summary, name, description, +9 more

get_event_orchestrationA
Read-onlyIdempotent

Get details for a specific event orchestration.

Args:
    orchestration_id: The ID of the event orchestration to retrieve

Returns:
    The event orchestration details

Inputs: orchestration_id (required). Returns: id, self, name, description, +8 more

get_event_orchestration_routerA
Read-onlyIdempotent

Get the router configuration for a specific event orchestration.

Args:
    orchestration_id: The ID of the event orchestration to retrieve router for

Returns:
    The event orchestration router configuration

Inputs: orchestration_id (required). Returns: orchestration_path

get_incidentA
Read-onlyIdempotent

Get a specific incident.

Args:
    incident_id: The ID or number of the incident to retrieve.

Returns:
    Incident details

Inputs: incident_id (required). Returns: id, summary, incident_number, status, +6 more

get_scheduleA
Read-onlyIdempotent

Get a specific schedule by ID.

Args:
    schedule_id: The ID of the schedule to retrieve

Returns:
    Schedule details

Inputs: schedule_id (required). Returns: id, summary, name, description, +8 more

get_serviceA
Read-onlyIdempotent

Get details for a specific service.

Args:
    service_id: The ID of the service to retrieve

Returns:
    The service details

Inputs: service_id (required). Returns: id, name, description, escalation_policy, +1 more

get_teamA
Read-onlyIdempotent

Get a specific team.

Args:
    team_id: The ID or name of the team to retrieve
Returns:
    Team details

Inputs: team_id (required). Returns: id, summary, name, description

get_user_dataA
Read-onlyIdempotent

Get the current user's data.

Returns:
    User: User name, role, id, and summary and teams

Inputs: no named parameters. Returns: id, summary, name, email, +2 more

list_alert_grouping_settingsB
Read-onlyIdempotent

List all alert grouping settings with optional filtering.

Args:
    query_model: Optional filtering parameters

Returns:
    List of alert grouping settings matching the query parameters

Inputs: query_model (required). Returns: response

list_escalation_policiesB
Read-onlyIdempotent

List escalation policies with optional filtering.

Returns:
    List of escalation policies matching the query parameters

Inputs: query_model (required). Returns: response

list_event_orchestrationsB
Read-onlyIdempotent

List event orchestrations with optional filtering.

Args:
    query_model: Optional filtering parameters

Returns:
    List of event orchestrations matching the query parameters

Inputs: query_model (required). Returns: response

list_incidentsA
Read-onlyIdempotent

List incidents with optional filtering.

Args:
    query_model: Optional filtering parameters

Returns:
    List of Incident objects matching the query parameters

Examples:
    Basic usage filtering by status:

    >>> from pagerduty_mcp.models import IncidentQuery
    >>> result = list_incidents(IncidentQuery(status=["triggered"]))
    >>> isinstance(result.response, list)
    True

    Multiple statuses with a limit:

    >>> result = list_incidents(IncidentQuery(status=["triggered", "acknowledged"], limit=10))

Inputs: query_model (required). Returns: response

list_oncallsB
Read-onlyIdempotent

List on-call schedules with optional filtering.

Returns:
    List of on-call schedules matching the query parameters

Inputs: query_model (required). Returns: response

list_schedulesB
Read-onlyIdempotent

List schedules with optional filtering.

Returns:
    List of schedules matching the query parameters

Inputs: query_model (required). Returns: response

list_schedule_usersA
Read-onlyIdempotent

List users in a schedule.

Args:
    schedule_id: The ID of the schedule

Returns:
    List of users in the schedule

Inputs: schedule_id (required). Returns: response

list_servicesB
Read-onlyIdempotent

List all services.

Args:
    query_model: Optional filtering parameters

Returns:
    List of services matching the query parameters

Inputs: query_model (required). Returns: response

list_team_membersA
Read-onlyIdempotent

List members of a team.

Args:
    team_id: The ID of the team

Returns:
    List of UserReference objects

Inputs: team_id (required). Returns: response

list_teamsB
Read-onlyIdempotent

List teams based on the provided query model.

Args:
    query_model: The model containing the query parameters
Returns:
    List of teams.

Inputs: query_model (required). Returns: response

list_usersA
Read-onlyIdempotent

List users, optionally filtering by name (query) and team IDs.

Args:
    query_model: Optional filtering parameters

Returns:
    List of users matching the criteria.

Inputs: query_model (required). Returns: response

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 20 tools

    Disambiguation5/5

    Each tool targets a distinct resource or specific sub-resource (e.g., get_escalation_policy vs list_escalation_policies, get_event_orchestration_router). No two tools have overlapping purposes, making selection unambiguous.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern using snake_case: get_<resource> for single items, list_<resource> for collections. There are no deviations or mixed conventions.

    Tool Count5/5

    With 20 tools covering the major PagerDuty resources (incidents, services, teams, users, schedules, escalation policies, etc.), the count is appropriate for a comprehensive read-only API surface.

    Completeness2/5

    The server is entirely read-only; there are no create, update, delete, or action tools (e.g., acknowledge incident, create service). This is a significant gap for most workflows, leaving agents unable to take any action.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server for the Splunk On-Call (VictorOps) API providing comprehensive incident management, on-call schedules, team administration, and alert reporting through natural language.
      2,004 PyPI
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      A modular MCP server exposing tools for integrating with services like GitHub, Redash, Jenkins, Figma, Jira, Confluence, Teams, Datadog, PagerDuty, Slack, and Presto, enabling users to manage these platforms through natural language via an MCP client.
      -
    • A
      license
      B
      quality
      F
      maintenance
      Enables management of PagerDuty incidents, services, schedules, and more directly from MCP-enabled clients, with embedded interactive UIs for incident command center, on-call management, and other features.
      63
      79
      Apache 2.0
    • A
      license
      B
      quality
      C
      maintenance
      Unified MCP server for DevOps engineers that provides real-time read and write access to Kubernetes, ArgoCD, Prometheus, and PagerDuty from any MCP-compatible AI agent.
      21
      92 npm
      4
      MIT