Calseta is under active development. APIs and features may change. We welcome feedback and contributions on GitHub.
Run Calseta locally
Calseta runs as a single stack: FastAPI server, MCP server, and PostgreSQL. Start everything with one command:| Service | Port | Description |
|---|---|---|
| FastAPI server | 8000 | REST API for alerts, incidents, enrichment, and more |
| MCP server | 8001 | Model Context Protocol server for AI agents |
| PostgreSQL | 5432 | Primary store and task queue |
Next steps
How It Works
Understand the five-step pipeline: ingest, normalize, enrich, contextualize, and dispatch.
Authentication
Create API keys and authenticate your requests.
Alert Sources
Connect Microsoft Sentinel, Elastic, Splunk, or a generic webhook.
MCP Setup
Connect your AI agent to Calseta via the MCP server.