A
licenseB
qualityC
maintenanceAn MCP server that enforces runtime authorization for tool calls using Stage0 policy validation, preventing AI agents from executing unauthorized actions before they happen.
6
MIT
No user-submitted related servers found.
Scored across 1 tool
With only one tool, there is no possibility of confusion. The tool's purpose is clearly defined as a policy check that returns ALLOW or DENY.
The single tool name 'check_action' follows a clear verb_noun convention and is internally consistent. There are no other names to conflict.
A single tool is too few for a server named 'warrant-mcp' which implies broader policy management. The scope appears severely limited.
The tool only checks actions against an existing policy but provides no tools to view, create, update, or delete policies. This is a significant gap—agents cannot manage the policy store, only query it.