AI agents use vapi_update_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.
The tool modifies existing data (assistant configuration) in a reversible manner. While 'update' could theoretically span Write or Execute depending on what assistant configuration changes trigger, the description indicates a standard partial update of resource properties rather than triggering code execution or external operations.
From the tool's definition Tool name contains 'update' and description explicitly states 'Update an existing assistant (partial update — only send the fields you want to change).' This is a modification operation on an existing resource.
Attacks that exploit this kind of access
Update an existing assistant (partial update — only send the fields you want to change). 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_update_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.
vapi_update_assistant 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_update_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 vapi_update_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.
vapi_update_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.
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 →