Medium Risk

create_voice_ai_action

Create a new action for a voice AI agent. Actions define specific behaviors and capabilities during calls.

How to control create_voice_ai_action ↓

AI agents use create_voice_ai_action to create or update resources in GoHighLevel MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GoHighLevel MCP Server environment.

Medium Risk

Creating a new action for a voice AI agent in a CRM system is a write operation—it creates and modifies configuration data for automated call behaviors. While this could enable subsequent Execute operations (the voice agent may then perform calls), the tool itself creates/configures data rather than executing calls directly.

From the tool's definition Tool name 'create_voice_ai_action' explicitly uses 'create' verb. Description states 'Create a new action for a voice AI agent' which defines system behavior. This is a reversible data creation operation that modifies Voice AI agent configuration.

Documented attack patterns abuse exactly the kind of access create_voice_ai_action gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and GoHighLevel MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_voice_ai_action:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_voice_ai_action": {
      "limits": [
        {
          "counter": "create_voice_ai_action_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create_voice_ai_action stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register GoHighLevel MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the create_voice_ai_action tool do? +

Create a new action for a voice AI agent. Actions define specific behaviors and capabilities during calls. It is categorised as a Write tool in the GoHighLevel MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_voice_ai_action? +

Register the GoHighLevel MCP Server MCP server in PolicyLayer and add a rule for create_voice_ai_action: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches GoHighLevel MCP Server. Nothing to install.

What risk level is create_voice_ai_action? +

create_voice_ai_action is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_voice_ai_action? +

Yes. Add a rate_limit block to the create_voice_ai_action rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block create_voice_ai_action completely? +

Set action: deny in the PolicyLayer policy for create_voice_ai_action. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides create_voice_ai_action? +

create_voice_ai_action is provided by the GoHighLevel MCP Server MCP server (busybee3333/go-high-level-mcp-2026-complete). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every GoHighLevel MCP Server tool call.

Deterministic rules across all 566 GoHighLevel MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

566 GoHighLevel MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.