AgentWatch
- Updated April 16, 2026
- nicofains1/agentwatch
Adds observability for multi-agent systems: detects cascade failures, tracks heartbeats, and replays forensic traces so you can debug agents in production.
About
AgentWatch is an MCP server that brings observability to multi-agent systems, with cascade-failure detection, heartbeat tracking, and forensic replay of past runs. A solo builder reaches for it to see why a chain of agents broke and to replay the sequence of events that led to a failure. It stores data in a local SQLite database path you configure.
- Multi-agent observability
- Cascade failure detection
- Heartbeats + forensic replay
- SQLite-backed
AgentWatch by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --env AGENTWATCH_DB=YOUR_AGENTWATCH_DB agentwatch -- npx -y @nicofains1/agentwatch mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | @nicofains1/agentwatch |
|---|---|
| Transport | STDIO |
| Auth | None |
| Last updated | April 16, 2026 |
| Repository | nicofains1/agentwatch ↗ |
What it does
Adds observability for multi-agent systems: detects cascade failures, tracks heartbeats, and replays forensic traces so you can debug agents in production.
Who is it for?
debugging and monitoring multi-agent pipelines
Skip if: single-shot prompt apps with no agents
What you get
- agent heartbeats
- forensic replay
- failure alerts
Recommended MCP Servers
Agent Audit McpImmutable audit trail for agent-to-agent interactions2
Agentguard47Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.4
Agentic Observability MCPAgent tracing, cost tracking, anomaly detection for LLM agents
Agent Incident Relay McpAgent Incident Relay MCP — Article 73 5-clock broadcaster.
Agent Infra Mcp18 tools: agent memory, API drift detection, and HMAC-signed trust receipts
Agentmonitorrelay McpAI agent run monitoring with incident replay and SLA receipts.