AI agents invoke vibekit_deploy 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 deployment of code to a hosting platform, which is an irreversible execution action with significant blast radius. While deployment itself may be reversible (unlike deletion), the act of deploying code to production constitutes execution of external operations whose effects depend on which repository/branch is specified.
From the tool's definition Tool description states 'Deploy a GitHub repo to VibeKit hosting.' The server description indicates it 'facilitates interaction with hosted AI agents and the execution of headless coding tasks' and enables 'control deployments.' Deploying code to hosting is a…
Attacks that exploit this kind of access
Deploy a GitHub repo to VibeKit hosting. 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_deploy: 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_deploy 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_deploy 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_deploy. 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_deploy 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 →