pagerduty-mcp-community
Provides tools to interact with your PagerDuty account, enabling management of incidents, services, schedules, event orchestrations, alert grouping settings, and more.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@pagerduty-mcp-community Show me the current ongoing incidents"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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-communityfor 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:
Navigate to User Settings. Click on your user profile icon, then select My Profile and then User Settings.
In your user settings, locate the API Access section.
Click the Create API User Token button and follow the prompts to generate a new token.
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:
Open Cursor settings (Cursor Settings > Tools > Add MCP, or
Cmd+,on Mac, orCtrl+,on Windows/Linux).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": "${input:pagerduty-api-key}" } } } }
VS Code Integration
You can configure this MCP server directly within Visual Studio Code's settings.json file, allowing VS Code to manage the server lifecycle.
Open VS Code settings (File > Preferences > Settings, or
Cmd+,on Mac, orCtrl+,on Windows/Linux).Search for "mcp" and ensure "Mcp: Enabled" is checked under Features > Chat.
Click "Edit in settings.json" under "Mcp > Discovery: Servers".
Add the following configuration:
{ "mcp": { "inputs": [ { "type": "promptString", "id": "pagerduty-api-key", "description": "PagerDuty API Key", "password": true } ], "servers": { "pagerduty-mcp": { "type": "stdio", "command": "uvx", "args": [ "pagerduty-mcp-community", "--enable-write-tools" // This flag enables write operations on the MCP Server enabling you to creating incidents, schedule overrides and much more ], "env": { "PAGERDUTY_USER_API_KEY": "${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)
Ensure MCP is enabled in VS Code settings (Features > Chat > "Mcp: Enabled").
Configure the server as described above.
Open the Chat view in VS Code (
View>Chat).Make sure
Agentmode is selected. In the Chat view, you can enable or disable specific tools by clicking the 🛠️ icon.Enter a command such as
Show me the latest incidentorList my event orchestrationsto interact with your PagerDuty account through the MCP server.You can start, stop, and manage your MCP servers using the command palette (
Cmd+Shift+P/Ctrl+Shift+P) and searching forMCP: 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.
Locate your Claude Desktop configuration file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
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" } } } }Replace the placeholder values:
Replace
/path/to/your/mcp-server-directorywith the full path to the directory where you cloned the MCP server (e.g.,/Users/yourname/code/pagerduty-mcp)Replace
your-pagerduty-api-key-herewith your actual PagerDuty User API TokenIf your PagerDuty account is located in the EU, update the API host to
https://api.eu.pagerduty.com
Restart Claude Desktop completely for the changes to take effect.
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
Clone the repository
Install
asdfpluginsasdf plugin add python asdf plugin add nodejs https://github.com/asdf-vm/asdf-nodejs.git asdf plugin add uvInstall tool versions using
asdf:asdf installCreate a virtual environment and install dependencies using
uv(now thatasdfhas set the correct Python anduvversions):uv syncEnsure
uvis available globally.The MCP server can be run from different places so you need
uvto 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.
Run it locally
To run your cloned PagerDuty MCP Server you need to update your configuration to use
uvinstead ofuvx."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-toolsflag. 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 toolsget_alert_grouping_settingBRead-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_policyBRead-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_orchestrationARead-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_routerARead-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_incidentARead-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_scheduleARead-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_serviceARead-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_teamARead-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_dataARead-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_settingsBRead-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_policiesBRead-onlyIdempotent
List escalation policies with optional filtering.
Returns:
List of escalation policies matching the query parameters
Inputs: query_model (required). Returns: response
list_event_orchestrationsBRead-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_incidentsARead-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_oncallsBRead-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_schedulesBRead-onlyIdempotent
List schedules with optional filtering.
Returns:
List of schedules matching the query parameters
Inputs: query_model (required). Returns: response
list_schedule_usersARead-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_servicesBRead-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_membersARead-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_teamsBRead-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_usersARead-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
Scored across 20 tools
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.
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.
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.
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
Pingstack monitors cron jobs and scheduled tasks with heartbeat checks, and checks websites, TCP ports, DNS records, SSL certificates and domain expiry. This MCP server lets your agent create, update, pause and delete checks, build dashboards and publish them as status pages, manage notification groups, and read incidents with their causes, uptime, run history and latency. Pause, delete and unpublish stay off until you turn them on. Browser sign-in, no API key needed.
Manage uptime monitors, incidents and status pages from any MCP client.
The official Planning Center MCP server for interacting with your ministry's data.
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP 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 PyPIMIT
- FlicenseNot gradedqualityDmaintenanceA 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.-

pagerduty-mcpofficial
AlicenseBqualityFmaintenanceEnables 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.6379Apache 2.0- AlicenseBqualityCmaintenanceUnified 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.2192 npm4MIT