AI agents call vibekit_agent_config to retrieve information from Vibekit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves configuration data without modifying system state. It is a straightforward query operation that returns information about an existing agent's model configuration. This poses minimal security risk as it only exposes existing configuration state without enabling changes, execution, or deletion.
From the tool's definition Tool description states it 'Get the AI agent configuration for an app' and 'Returns the current model.' The verb 'Get' and 'Returns' indicate a read-only retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get the AI agent configuration for an app. Returns the current model. It is categorised as a Read tool in the Vibekit MCP Server, which means it retrieves data without modifying state.
Register the Vibekit MCP server in PolicyLayer and add a rule for vibekit_agent_config: 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_config is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the vibekit_agent_config 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_config. 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_config 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 →