A
licenseNot graded
qualityC
maintenanceA pre-action authorization server for AI agents that classifies tool calls into 14 intent categories, scores risk 0-100, and produces deterministic allow/deny/ask decisions with full audit trail.
MIT
No user-submitted related servers found.
Scored across 1 tool
Only one tool exists, so there is no possibility of ambiguity.
The single tool name 'forecast' is concise and follows a clear verb pattern, which is trivially consistent.
A single generic risk assessment tool seems under-scoped for the stated domain of any irreversible action; typically 3-15 tools would be expected.
The tool covers a broad need but lacks domain-specific variations or configuration options, leaving notable gaps for nuanced use cases.