---
id: pagerduty-mcp
version: "1.1.0"
license: unclear
license_treatment: unclear
maintenance: active
---

# pagerduty-mcp — PagerDuty's official local MCP (Model Context Protocol) server which provides tools to interact with your PagerDuty account directly from your MCP-enabled client.

License: unclear · Maintenance: active · Downloads: 116.9K/mo

## What it is and what it does

pagerduty-mcp is a local MCP server that bridges your PagerDuty account to AI assistants running in VS Code, Cursor, and Claude Desktop. It exposes PagerDuty operations—incident management, schedule overrides, escalation policies, service dependencies, and event orchestrations—as tools callable from your IDE's chat interface, letting you query and manage on-call operations without leaving your editor.

The package bundles embedded React applications for incident lifecycle management, on-call scheduling, compensation reporting, and service dependency visualization. It requires a PagerDuty User API Token for authentication and runs as a stdio-based MCP server managed by your IDE. Python 3.12 is required; installation is straightforward via pip, and configuration happens in your IDE's settings file.

Use it for:

- Query and acknowledge PagerDuty incidents directly from VS Code Chat while coding, without switching to the web UI.
- Create and manage schedule overrides and escalation policies through Claude Desktop during incident response.
- View on-call compensation metrics and fairness scoring across responders for compliance and team planning.
- Visualize service dependency graphs to understand blast radius during incident investigation.
- Onboard new PagerDuty accounts step-by-step through the embedded wizard without manual API calls.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

An MCP (Model Context Protocol) server that connects AI assistants in VS Code, Cursor, and Claude Desktop to your PagerDuty account, exposing tools to manage incidents, schedules, services, and event orchestrations.

Yes, if you use VS Code, Cursor, or Claude Desktop and manage PagerDuty incidents regularly. The low install friction and active maintenance make it a practical choice for IDE-native incident management. However, clarify the license terms first, and verify Python 3.12 compatibility in your environment. The unclear license status is the main blocker—resolve that before production use.

## Install

pip install pagerduty-mcp
uv add pagerduty-mcp
poetry add pagerduty-mcp

## Installing pagerduty-mcp

Before you install: Low install friction with a pure-Python wheel. Marked active with a recent release. Requires Python 3.12 specifically (not a range), which narrows compatibility; verify your environment matches before installing.

License in practice: License status is unclear—no SPDX identifier or raw license text is available in the package metadata. Clarify the license terms with PagerDuty or the project repository before using in production or distributing.

Quickstart:

# Install
pip install pagerduty-mcp

# Configure in VS Code settings.json under mcp.servers:
# {
#   "pagerduty-mcp": {
#     "type": "stdio",
#     "command": "uvx",
#     "args": ["pagerduty-mcp", "--enable-write-tools"],
#     "env": {"PAGERDUTY_USER_API_KEY": "your-token"}
#   }
# }

# Then in VS Code Chat (Agent mode):
# "Show me the latest incident"

Requires Python 3.12 exactly (~=3.12.0). Requires a PagerDuty User API Token and an MCP-enabled client (VS Code with MCP enabled, Cursor, or Claude Desktop). The uv package manager is recommended for running the server.

Verify before relying:

- Whether the package is truly maintained by PagerDuty or is a community project (no repo URL in metadata).
- Exact scope of write operations enabled by --enable-write-tools flag and any audit/safety constraints.
- Whether embedded React UIs (Incident Command Center, On-Call Manager, etc.) are fully functional or partially documented.
- Support status and SLA for this MCP server vs. the main PagerDuty API.

## Package facts

- License: not declared (unclear)
- Python support: capped_below_current
- Install friction: low
- Maintenance: active
- Downloads: 116.9K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

pagerduty integration mcp, incident management ai assistant, pagerduty api client, on-call schedule management, mcp server pagerduty, claude pagerduty tools, incident response automation, mcp-server, incident-management, pagerduty-integration

[View on SkillFed](https://skillfed.io/packages/pagerduty-mcp) · [View on PyPI](https://pypi.org/project/pagerduty-mcp/)