search_docs

What search_docs does on CogniRepo

AI agents call search_docs 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 search_docs is rated Low

This tool retrieves information from a static documentation index without creating, modifying, deleting, or executing any operations. It returns results based on semantic matching, which is a passive data retrieval pattern. The blast radius of misuse is minimal — an agent could retrieve irrelevant or excessive documentation, but cannot alter state, execute code, or cause harm.

From the tool's definition Tool performs 'Search indexed documentation files...by semantic similarity' — a retrieval operation with no modification or side effects. The verb 'search' and the read-only nature of querying indexed documentation confirm this is a Read operation.

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

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

Questions about search_docs