10 actions in 3 pieces of software · ranked by words, meaning and measured trust · 496 ms
- 1agentwatchfound in code, not yet checkedno passport yet
- agentwatch_report_heartbeat
Report a heartbeat for an agent. Call this periodically to track agent health.
- agentwatch_dashboard
Fleet health overview - shows all agents, their status, uptime, and active alert counts
- agentwatch_fleet_health
Get health status of all agents with uptime percentages
- agentwatch_trace
Record a trace event for cross-agent action tracking
- agentwatch_get_alerts
List active (unresolved) alerts, optionally filtered by agent
- agentwatch_report_heartbeat
- 2AgentWatchfound in code, not yet checkedno passport yet
- get_session_events
Return the raw events for a given session ID. JSONL for file-based agents (Claude/Codex/Gemini/OpenClaw); Hermes messages are serialized as one JSON object per line. Use after list_recent_sessions to drill into a session.
- get_tool_usage_stats
Aggregate tool invocation counts, total duration, and error counts. If sessionId is given, stats are scoped to that session; otherwise scoped to the N most recently active sessions across all agents (default 50).
- list_recent_sessions
List the most recent local agent sessions across Claude Code, Codex, Gemini, OpenClaw, and Hermes, newest first. Use to find a session to inspect.
- search_sessions
Substring search across all local agent session files. Returns matching sessions with the first few matching lines. Covers Claude, Codex, Gemini, OpenClaw, and Hermes.
- get_session_events
- 3agentwatchfound in code, not yet checkedno passport yet
MCP serverpeitsan/agentwatch
- agentwatch_pair_status
Report whether the relay link is up and which Companion peers are paired.
- agentwatch_pair_status
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.