AI agents call vibekit_account 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 account metadata without side effects. It does not create, modify, delete, or execute operations. The severity is low because account info exposure has limited blast radius compared to tools that could modify deployments, execute code, or delete data. Confidence is high because the description is explicit about read-only operations.
From the tool's definition Tool name and description indicate it retrieves account information: 'Get VibeKit account info — plan, credits balance, session usage, and limits.' The verb 'Get' and the list of data fields (plan, credits, usage, limits) are all informational queries with no…
Attacks that exploit this kind of access
Get VibeKit account info — plan, credits balance, session usage, and limits. 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_account: 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_account 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_account 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_account. 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_account 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 →