AI agents call vapi_list_phone_numbers to retrieve information from Mcp Vapi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists existing data (phone numbers) from the Vapi account without creating, modifying, deleting, or executing any operations. It is informational only, supporting other tools by providing identifiers. The blast radius if misused is minimal—an agent gains visibility into account phone numbers but cannot take actions with them or access sensitive call content.
From the tool's definition Tool name 'vapi_list_phone_numbers' and description 'List all phone numbers in your Vapi account' indicate a pure query/retrieval operation with no side effects.
Attacks that exploit this kind of access
List all phone numbers in your Vapi account. Use the IDs when creating calls. It is categorised as a Read tool in the Mcp Vapi MCP Server, which means it retrieves data without modifying state.
Register the Mcp Vapi MCP server in PolicyLayer and add a rule for vapi_list_phone_numbers: 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_list_phone_numbers is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the vapi_list_phone_numbers 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_list_phone_numbers. 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_list_phone_numbers 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 →