vapi_create_assistant · Mcp Vapi MCP: Risk & Policy

WHAT IT DOES

What vapi_create_assistant does on Mcp Vapi

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

WHY IT NEEDS A POLICY

Why vapi_create_assistant needs a policy

This tool creates a new resource (a voice assistant) with reversible persistence. While creation itself is Write-category, the severity is elevated to 'high' because: (1) created voice assistants can be used to make outbound calls (per server description), (2) they are configured with system prompts and LLM models that shape their behavior, and (3) a compromised agent could create assistants for unauthorized…

From the tool's definition Tool description states 'Create a new Vapi voice assistant' with configuration of name, first message, system prompt, LLM model, and voice settings. This is a creation operation that modifies backend state by instantiating a new resource.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

vapi_create_assistant Rate-limited

vapi_create_assistant 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "vapi_create_assistant": {
      "limits": [
        {
          "counter": "vapi_create_assistant_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mcp Vapi, so you can run agents against it safely.

FAQ

Questions about vapi_create_assistant

What does the vapi_create_assistant tool do? +

Create a new Vapi voice assistant. You can set its name, first message, system prompt, LLM model, voice, and more. It is categorised as a Write tool in the Mcp Vapi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on vapi_create_assistant? +

Register the Mcp Vapi MCP server in PolicyLayer and add a rule for vapi_create_assistant: 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 Mcp Vapi. Nothing to install.

What risk level is vapi_create_assistant? +

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

Can I rate-limit vapi_create_assistant? +

Yes. Add a rate_limit block to the vapi_create_assistant 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 vapi_create_assistant completely? +

Set action: deny in the PolicyLayer policy for vapi_create_assistant. 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 vapi_create_assistant? +

vapi_create_assistant is provided by the Mcp Vapi MCP server (adhirajhangal/mcp-vapi). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.