add

What add does on Test

AI agents invoke add to trigger actions in Test. 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 add is rated High

The description 'Runs' strongly implies execution of a command or process. The server context involves build/test tooling, and sibling tools like 'add-package', 'ansible-playbook', 'bazel' suggest this server executes external operations. The incomplete description lowers confidence, but 'Runs' is the key evidence for Execute classification. Severity is medium as it likely installs or adds a dependency/component.

From the tool's definition Tool name is 'add' with description only saying 'Runs' — description is truncated/uninformative, but combined with server context (test frameworks: pytest, jest, vitest, mocha) and sibling tools (ansible-playbook, bazel, etc.), 'add' likely executes a command…

The rule that runs add safely

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

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

Questions about add