convex_deploy

What convex_deploy does on Yaver

AI agents invoke convex_deploy to trigger actions in Yaver. 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.

Parameters from the server's own tool schema.

Why convex_deploy is rated High

Deploying Convex functions is an Execute action—it runs a deployment pipeline that triggers external operations and has side effects that depend on the arguments provided. It is not merely Write (creating/modifying data reversibly in a local context) because deployment affects live infrastructure. It is not Destructive because deployment itself is reversible through redeployment.

From the tool's definition Tool name 'convex_deploy' and description 'Deploy Convex functions' indicate triggering a deployment operation, which executes external operations (deploying code/infrastructure) whose effects depend on which functions are specified as arguments.

Risk signalsAccepts file system path (directory)

The rule that runs convex_deploy safely

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

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

Questions about convex_deploy