AI agents use book_appointment to create or update resources in Mindbody — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mindbody environment.
This tool creates a new appointment booking, which is a reversible write operation (appointments can typically be cancelled). However, it has high severity because it commits a client to a scheduled time slot with a staff member, potentially triggering holds, deposits, or cancellation fees. The environment gate (MINDBODY_ALLOW_BOOKINGS) further indicates it is a consequential action requiring explicit enablement.
From the tool's definition 'Schedule a single wellness or training appointment for a client with a specific staff member at a specific time. GATED behind MINDBODY_ALLOW_BOOKINGS.'
Attacks that exploit this kind of access
Schedule a single wellness or training appointment for a client with a specific staff member at a specific time. GATED behind MINDBODY_ALLOW_BOOKINGS. Returns an error if not enabled. It is categorised as a Write tool in the Mindbody MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mindbody MCP server in PolicyLayer and add a rule for book_appointment: 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_appointment is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the book_appointment 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_appointment. 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_appointment 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 →