Reset an app
AI agents call vibekit_agent_reset to permanently remove resources in Vibekit — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Resetting an app implies destroying current runtime state, configuration, or data and returning to an initial state. This action is generally irreversible — any unsaved state, sessions, or in-progress work would be lost. Given the server context involves AI agents, deployments, and database operations, a reset could wipe agent history, environment configuration, or database state.
From the tool's definition 'Reset an app' — resetting an application typically involves clearing state, wiping data, or reverting to a baseline configuration in an irreversible manner.
Attacks that exploit this kind of access
Reset an app. It is categorised as a Destructive tool in the Vibekit MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Vibekit MCP server in PolicyLayer and add a rule for vibekit_agent_reset: 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_agent_reset is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the vibekit_agent_reset 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_agent_reset. 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_agent_reset 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 →