About MCP PagerDuty
MCP PagerDuty is an early-stage PagerDuty integration for AI assistants and MCP clients seeking incident information. Its README lists incident tools, but also states that the API integration is not yet implemented.
Key features
- 01Planned incident listing tool
- 02Planned incident detail retrieval
- 03Planned incident notes retrieval
- 04PagerDuty API integration not yet built
Use cases
- 01Plan MCP-based incident lookup
- 02Plan retrieval of incident details and notes
MCP support
It is intended to expose PagerDuty incident listing, details, and notes tools to MCP clients. The README says the API integration is not yet implemented.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP PagerDuty
🚧 Early Development - Work in Progress 🚧
A Model Context Protocol (MCP) server that provides integration with PagerDuty for incident management and monitoring operations.
⚠️ Project Status
This project is in its initial development phase. Many features are planned but not yet implemented. Contributions and feedback are welcome!
🚀 Getting Started
Prerequisites
- Python 3.13 or higher
- PagerDuty API token
Installation
-
Clone the repository
git clone https://github.com/judexzhu/mcp-pagerduty.git cd mcp-pagerduty -
Install dependencies with UV
uv sync -
Configure environment
cp .env.example .env # Edit .env with your PagerDuty API credentials
Configuration
Create a .env file with your PagerDuty configuration:
PAGERDUTY_API_TOKEN=your_api_token_here
PAGERDUTY_API_URL=https://api.pagerduty.com
Note: PAGERDUTY_API_URL is optional and defaults to https://api.pagerduty.com if not specified.
🔧 Development
This project is actively under development. Current structure:
mcp-pagerduty/
├── pagerduty.py # Main MCP server implementation
├── pyproject.toml # Project configuration
├── .env # Environment variables (create from .env.example)
└── README.md # This file
Running the Server
python pagerduty.py
📚 MCP Integration
This server implements the Model Context Protocol to provide PagerDuty functionality to AI assistants and other MCP clients.
Current Tools
pagerduty_list_incidents- List incidents with filtering optionspagerduty_get_incident- Get detailed incident informationpagerduty_get_incident_notes- Get detailed incident information
Planned Resources
- Incident templates
- Escalation policy information
- Service status dashboards
🤝 Contributing
This project is in early development and contributions are very welcome!
How to Contribute
- Fork the repository
- Create a feature branch
git checkout -b feature/your-feature-name - Make your changes
- Add tests (when testing framework is set up)
- Submit a pull request
Development Priorities
Current development priorities:
- 🔴 High Priority: Basic incident listing and retrieval
- 🟡 Medium Priority: Incident creation and updates
- 🟢 Low Priority: Advanced features like escalation management
📋 TODO
- Implement basic MCP server structure
- Add PagerDuty API client
- Implement incident management tools
- Add comprehensive error handling
- Write tests
- Add logging and monitoring
- Create example configurations
- Write comprehensive documentation
🐛 Known Issues
- Project is in initial development phase
- No functionality implemented yet
- API integration not yet built
📖 Resources
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🆘 Support
Since this project is in early development:
- 📝 Documentation: Coming soon
- 🐛 Bug Reports: Please open an issue
- 💡 Feature Requests: Welcome via issues
- 💬 Questions: Open a discussion or issue
Note: This project is not affiliated with PagerDuty, Inc. It's a community-driven integration for the Model Context Protocol.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.