Overview
What is Incident.io MCP Server?
A Model Context Protocol server that integrates with Incident.io, enabling AI agents to list incidents, view severities, and create new incidents via HTTP. It is built for developers using MCP-compatible clients.
How to use Incident.io MCP Server?
Install globally or locally via npm, set the required API_KEY environment variable, optionally set PORT, and run the server. Then configure your MCP client to connect to the server’s HTTP endpoints.
Key features of Incident.io MCP Server
- Integration with Incident.io API
- List latest incidents
- View available severities
- Create new incidents
- Health check endpoint
- Configurable port (default 3000)
Use cases of Incident.io MCP Server
- Automate incident response workflows from AI assistants
- Query current incident status and severity without manual checks
- Create incidents programmatically during on-call automation
FAQ from Incident.io MCP Server
What environment variables are required?
A valid Incident.io API key must be set in the API_KEY environment variable. The PORT variable is optional, defaulting to 3000.
How do I install the server?
Install globally with npm install -g github:stuartphilp/incident-io-mcp-server, or clone the repository, run npm install and npm run build.
What runtime dependencies are needed?
Node.js and npm are required to install and run the server.
Does the server provide a health check?
Yes, a GET /health endpoint is available to verify the server is running.
What transports and authentication does it use?
The server exposes HTTP endpoints and authenticates via the API_KEY environment variable passed as an HTTP header (implementation detail not documented further in the README).
