AI agents call book_client_to_class to retrieve information from Mindbody without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though book_client_to_class only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Enroll a client into an upcoming studio class. GATED behind MINDBODY_ALLOW_BOOKINGS env var. Returns an error if not enabled. This action results in a real reservation. It is categorised as a Read tool in the Mindbody MCP Server, which means it retrieves data without modifying state.
Register the Mindbody MCP server in PolicyLayer and add a rule for book_client_to_class: 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 Mindbody. Nothing to install.
book_client_to_class 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 book_client_to_class 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 book_client_to_class. 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.
book_client_to_class is provided by the Mindbody MCP server (nobanks/mindbody-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 →