Creates a new Vapi tool
AI agents use create_tool to create or update resources in Vapi MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vapi MCP Server environment.
This tool creates new tools within the Vapi voice AI system. It is a reversible write operation (new tools can be deleted or modified later), not a destructive action. The severity is medium because creating tools could potentially enable unintended voice AI behaviors if misconfigured, but the operation itself is not irreversible and does not directly execute code or move money.
From the tool's definition Tool name 'create_tool' and description 'Creates a new Vapi tool' indicate a create operation that adds new data/configuration to the Vapi platform.
Attacks that exploit this kind of access
Creates a new Vapi tool. It is categorised as a Write tool in the Vapi MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vapi MCP Server MCP server in PolicyLayer and add a rule for create_tool: 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 Vapi MCP Server. Nothing to install.
create_tool is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_tool 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.
Set action: deny in the PolicyLayer policy for create_tool. 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.
create_tool is provided by the Vapi MCP Server MCP server (kuchikirenji/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →