AI agents use vibekit_create_app to create or update resources in Vibekit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vibekit environment.
Creating a new hosted application is a Write operation—it creates new data/resources that persist and can be modified later, but is reversible (apps can be deleted). The severity is high because creating an app could: consume cloud resources/costs, potentially lock in dependencies, or enable deployment of arbitrary code.
From the tool's definition Tool name 'vibekit_create_app' and description 'Create a new hosted app from a template' indicate creation of a new resource with persistent effects.
Attacks that exploit this kind of access
Create a new hosted app from a template. It is categorised as a Write tool in the Vibekit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vibekit MCP server in PolicyLayer and add a rule for vibekit_create_app: 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 Vibekit. Nothing to install.
vibekit_create_app 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 vibekit_create_app 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 vibekit_create_app. 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.
vibekit_create_app is provided by the Vibekit MCP server (vibekit-apps/vibekit-mcp). 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 →