get_context

What get_context does on Chitta

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

Why get_context is rated Low

This tool retrieves pre-stored knowledge from the memory system without modifying data or executing external operations. It is purely a read operation that queries the knowledge graph or vector memory. The severity is low because retrieval alone poses minimal risk; misuse would expose existing data rather than destroy, modify, or execute arbitrary code.

From the tool's definition Tool name 'get_context' and description 'Recall stored knowledge' indicate a retrieval operation. The phrase 'could touch the user' suggests data access rather than modification. No creation, deletion, or external execution capabilities are evident.

The rule that runs get_context safely

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

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

Questions about get_context