Gets a Vapi assistant by ID
AI agents call get_assistant to retrieve information from Vapi MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves configuration or state information about an existing assistant without modifying, executing, or deleting anything. It is a simple query/fetch operation that fits the Read category. Severity is low because retrieving assistant metadata poses minimal risk even if misused by an agent.
From the tool's definition Tool name is 'get_assistant' and description states 'Gets a Vapi assistant by ID' — a straightforward retrieval operation with no side effects.
Attacks that exploit this kind of access
Gets a Vapi assistant by ID. It is categorised as a Read tool in the Vapi MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Vapi MCP Server MCP server in PolicyLayer and add a rule for get_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 Vapi MCP Server. Nothing to install.
get_assistant 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 get_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.
Set action: deny in the PolicyLayer policy for get_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.
get_assistant 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 →