proofread_text

What proofread_text does on AirMCP

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

Why proofread_text is rated Low

Proofreading is a read-operation: it analyzes input text and returns suggestions/corrections but does not create, modify, delete, execute code, or commit financial transactions. The tool is stateless and non-destructive. While it processes user content through an AI model, the output is advisory only, leaving any application of corrections to the user. This poses minimal security risk.

From the tool's definition The tool 'proofread_text' uses Apple Intelligence to 'proofread and correct grammar/spelling' — this is a read-only analysis operation that examines text and returns corrections without modifying the underlying data or triggering side effects.

The rule that runs proofread_text safely

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

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

Questions about proofread_text