delimit_screenshot

What delimit_screenshot does on Delimit

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

Why delimit_screenshot is rated Low

Screenshots capture and retrieve information from the user's screen or workspace without creating, modifying, or deleting data. This fits the Read category (retrieves data with no side effects). Severity is medium rather than low because screenshots could expose sensitive information, credentials, or private data visible on screen, making them a moderate information disclosure risk if misused by an AI agent.

From the tool's definition Tool name 'delimit_screenshot' indicates screenshot capture functionality. The description is empty, but screenshot tools typically retrieve visual state without modifying data.

The rule that runs delimit_screenshot safely

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

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

Questions about delimit_screenshot