lint

What lint does on Build

AI agents invoke lint to trigger actions in Build. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Why lint is rated High

Linting tools execute external processes or shell commands to analyze code. The server is described as a 'build tool' that runs commands like tsc and generic commands. 'Runs' in the description confirms execution behavior. Misuse could lead to unintended code execution or resource exhaustion, but blast radius is generally medium as linting is typically read-only in effect, though it does execute external processes.

From the tool's definition Tool name 'lint' combined with server description mentioning 'runs' (truncated description: 'Runs') indicates it executes a linting command/process against code

The rule that runs lint safely

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

{
  "version": "1",
  "default": "deny",
  "tools": {
    "lint": {
      "limits": [
        {
          "counter": "lint_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about lint