get_service_endpoints

What get_service_endpoints does on CogniRepo

AI agents call get_service_endpoints to retrieve information from CogniRepo without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why get_service_endpoints is rated Low

With an empty description, confidence is reduced. The name strongly suggests retrieving service endpoint data (Read category), which is non-destructive. Severity is medium rather than low because exposing service endpoints could enable reconnaissance for attacks on backend systems if an AI agent misuses this data or leaks it, though the tool itself has no direct side effects.

From the tool's definition Tool name 'get_service_endpoints' suggests retrieval of endpoint information (a Read operation). Context indicates this is a persistent memory/knowledge graph server for AI tools.

The rule that runs get_service_endpoints safely

PolicyLayer is an MCP gateway: it sits between your AI agents and CogniRepo, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_service_endpoints, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_service_endpoints": {}
  }
}

Questions about get_service_endpoints