AI agents use vapi_create_squad 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.
This tool creates a new squad resource (a collection of voice assistants configured for handoff workflows), which is a Write operation that adds data to the system reversibly. While squad creation could enable complex call flows, the tool itself only creates/configures the squad structure; it does not execute calls, delete data, or move money.
From the tool's definition Tool description states 'Create a squad of assistants' — explicitly a creation operation that modifies data by adding a new squad resource to the Vapi.ai system.
Attacks that exploit this kind of access
Create a squad of assistants that can hand off to each other on a call. Great for receptionist → qualifier → closer flows. 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.
Register the Mcp Vapi MCP server in PolicyLayer and add a rule for vapi_create_squad: 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.
vapi_create_squad 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 vapi_create_squad 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 vapi_create_squad. 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.
vapi_create_squad 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.
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 →