org_search

What org_search does on CogniRepo

AI agents call org_search 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 org_search is rated Low

The tool searches data without modifying it, placing it in the Read category. Severity is medium rather than low because search across organizational/agent context could expose sensitive information or allow enumeration of private data if the agent is compromised. However, no direct side effects or data modification occur.

From the tool's definition Tool name 'org_search' and server context indicate querying/searching organizational or contextual data within a persistent memory system. Related sibling tools include 'cross_repo_search' and 'episodic_search', which are clearly Read operations.

The rule that runs org_search 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 org_search, this is the rule to start with:

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

Questions about org_search