Grade B
Sunaiva Gate — Agent Rule Enforcement
io.sunaivacore/gate · v2.0.4 · 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
MCP enforcement layer that intercepts AI agent actions and blocks rule violations before execution.
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 16 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (delete_custom_rule). Require confirmation before the agent calls them. |
What was checked
- https://mcp.sunaivacore.io: answers without auth
- npm: @sunaiva/gate@2.0.4 (static checks only; code not executed)
Public tools: validate_action, log_bypass, get_rules, update_rules, get_audit_log, ship_confidence_check, audit_verify, set_rule_mode, get_rule_modes, reset_rule_mode, add_custom_rule, update_custom_rule, delete_custom_rule, list_custom_rules, list_presets, apply_preset
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-sunaivacore-gate-0044ef6e)