Grade B
AgentWatch
dev.workers.agentwatch.agentwatch/agentwatch · v0.5.1 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Read-only watchtower for AI agents on-chain: decoded receipts, plan vs execution, Safe audits.
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 21 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (remove_recovery_owner). Require confirmation before the agent calls them. |
What was checked
- https://agentwatch.agentwatch.workers.dev/mcp: answers without auth
Public tools: list_watched, get_feed, run_audit, get_capabilities, get_alerts, get_pending_proposals, get_fidelity, get_leaderboard, get_benchmark, get_tca, register_intent, add_watch, watch_demo_set, refresh_watches, get_agent_passport, set_agent_passport, list_recovery_owners, set_recovery_owner, remove_recovery_owner, get_safe_defaults, get_dashboard
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/dev-workers-agentwatch-agentwatch-agentwatch-b4fef8b2)