AI agents invoke vibekit_stop_app to trigger actions in Vibekit. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external operation (stopping a hosted application) whose effects depend on which app is targeted. While not destructive (data persists) or financial, it is Execute-level because it causes immediate state changes to deployed infrastructure and can impact service availability.
From the tool's definition Tool name 'vibekit_stop_app' and description 'Stop a hosted app' indicate an action that terminates a running service. Stopping an app is an external operation with immediate effects on system state and availability.
Attacks that exploit this kind of access
Stop a hosted app. It is categorised as a Execute tool in the Vibekit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Vibekit MCP server in PolicyLayer and add a rule for vibekit_stop_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_stop_app is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the vibekit_stop_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_stop_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_stop_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 →