
AgentWatch
Gives you post-mortem tools for multi-agent systems. Agents call `report()` for heartbeats and `trace()` for actions, linking them by trace ID and parent event. When something fails, `correlate()` walks backward through the chain to find the root cause. Exposes 13 MCP tools including `agentwatch_cascade`, `agentwatch_replay`, and `agentwatch_dashboard` so Claude can diagnose why your swarm fell over. Stores everything in local SQLite, works with any agent framework. The CLI lets you run `npx @nicofains1/agentwatch demo` to see a 5-agent cascade failure traced soup to nuts. Useful if you're running CrewAI, AutoGen, or custom agents and need forensics when one failure triggers three others.
- tools
- 13
- transport
- STDIO
- env var
- 1
- last updated
- Mar 16, 2026
Tools
13 toolsPublic tool metadata for what this MCP can expose to an agent.
agentwatch_dashboardFleet health overview.
Fleet health overview.
No parameter schema in public metadata yet.
agentwatch_report_heartbeat
No parameter schema in public metadata yet.
agentwatch_trace
No parameter schema in public metadata yet.
agentwatch_cascade
No parameter schema in public metadata yet.
agentwatch_replay
No parameter schema in public metadata yet.
agentwatch_get_alerts
No parameter schema in public metadata yet.
agentwatch_get_failures
No parameter schema in public metadata yet.
agentwatch_get_trace
No parameter schema in public metadata yet.
agentwatch_fleet_health
No parameter schema in public metadata yet.
agentwatch_create_trace_id
No parameter schema in public metadata yet.
agentwatch_alert
No parameter schema in public metadata yet.
agentwatch_resolve_alert
No parameter schema in public metadata yet.
agentwatch_dashboard_text
No parameter schema in public metadata yet.
Sponsors
Configuration
AGENTWATCH_DBPath to SQLite database file
Readme
agentwatch
Your agent swarm crashed at 2am. You have logs from 10 agents and no idea which one started the cascade. AgentWatch tells you.
It tracks heartbeats, links actions across agents, walks backward from any failure to the root cause, and replays the full sequence. Works with any agent framework (CrewAI, AutoGen, LangGraph, PocketFlow, custom). Stores everything in a local SQLite file.
Early stage. Issues and feedback welcome: https://github.com/nicofains1/agentwatch/issues
See it in action
No install needed:
npx @nicofains1/agentwatch demo
This seeds a 5-agent fleet, triggers a cascade failure, and shows you the full trace:
AgentWatch Fleet Dashboard
============================================================
Agents: 5 total | 3 healthy | 1 degraded | 1 error | 0 offline
Details
- Repository
- github.com/nicofains1/agentwatch
- Categories
- AI & LLM Tools, Monitoring & Observability
- Package
@nicofains1/agentwatch- Transport
- STDIO
- Registry
- MCP registry, active