Atlas / MCP servers / pagerduty / PagerDuty

PagerDutySAFE

mcp/pagerduty/pagerduty-1

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

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
—
Transport
sse · stdio · streamable-http
License
Apache-2.0
Stars
79
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[!IMPORTANT] This repository is deprecated and now read-only. Development has moved to PagerDuty's hosted Remote MCP Server — see the docs there for setup instructions.

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.

Quick start

You need `uv` and a PagerDuty User API Token — see Prerequisites and Authentication.

PAGERDUTY_USER_API_KEY="your-token" uvx pagerduty-mcp

By default only read-only tools are exposed. Add --enable-write-tools to allow tools that modify your PagerDuty account. Then point your MCP client at the server — Cursor, VS Code, Claude Desktop, or Docker.

Prefer no local install? PagerDuty hosts a Remote MCP Server with OAuth support.

Contents

The full documentation lives in docs/ and is readable directly on GitHub.

Getting Started

  • Introduction — what the MCP server is and what it can do
  • Prerequisites
  • Quick Start
  • Authentication

Installation

  • Cursor
  • VS Code
  • Claude Desktop
  • Docker

Remote Server

  • [Remote MCP Server Setup](https://support.pagerduty.com/main
Read from source at commit ea4cc3b59b18OBSERVED · 2026-10-07
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code (pypi)
claude mcp add pagerduty-mcp -- uvx pagerduty-mcp==0.2.1 --enable-write-tools
03

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (2 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (4)

LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
tests/evals/llm_clients/bedrock_client.py:56
decoded_url = base64.b64decode(encoded_url).decode("utf-8")
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
docs/experimental/oncall-compensation.md:3
The **On-Call Compensation Report** is an interactive data table that breaks down on-call burden by person — hours scheduled, incidents responded to, off-hours interruptions, compliance status, and fa
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
LOWInventory / provenance · mcp.no_tools_extracted · CWE-1104
server.json
Why it matters. the tool list is enumerated at runtime by tools/list, not declared in source
Fix. the page says so rather than showing an empty table
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
docs/getting-started/prerequisites.md:15
curl -LsSf https://astral.sh/uv/install.sh | sh

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha ea4cc3b59b18full audit observations/trust-audit/mcp-server/pagerduty__pagerduty-1.json · Report an issue / request a re-scan
04

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-07ea4cc3b59b18SAFEB89first audit
05

Questions

What is the PagerDuty MCP server?

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

Is PagerDuty safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does PagerDuty need?

It reads AWS_BEARER_TOKEN_BEDROCK, OPENAI_API_KEY and PAGERDUTY_USER_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does PagerDuty run?

It speaks sse, stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as pagerduty-mcp.

How current is this page?

The grade is for one exact copy of the source (ea4cc3b59b18), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement