Back to Directory/Monitoring & Observability

io.github.KryptosAI/agent-observability

Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.

Monitoring & Observabilityv1.0.7
View on GitHub

Learn More

PagerDuty MCP Server: AI Incident Response With ClaudePagerDuty's official MCP server exposes 70+ tools for incidents, on-call schedules, and escalation policies. This guide covers the local read-only-by-default server, the newer hosted OAuth endpoint, and how it slots into an AI on-call stack next to Grafana and Datadog.Read articleGrafana MCP Server: Query Metrics and Alerts With ClaudeGrafana's official MCP server, grafana/mcp-grafana, lets Claude query Prometheus metrics, Loki logs, dashboards, and alerting rules directly. This guide covers the full tool surface, the new hosted remote option Grafana Labs previewed in 2026, and where it fits alongside Datadog and Sentry.Read articleDatadog MCP Server: Observability and Monitoring with ClaudeDatadog has an official MCP server that lets Claude and Cursor query metrics, read logs, check monitors, and surface dashboards. This guide covers installation, authentication, the full tool surface, and how to scope your API key for safe read-only agent access to production observability data.Read article