create_patient
AI agents use create_patient to create or update resources in Cliniko MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cliniko MCP Server environment.
Creating a patient record in a practice management system is a reversible Write operation—it adds data to the system but can theoretically be undone (unlike deletion). However, severity is high because patient records are sensitive healthcare data with regulatory implications (HIPAA, PIPEDA, GDPR), and malicious patient creation could enable downstream fraudulent invoicing, appointment manipulation, or data…
From the tool's definition Tool name 'create_patient' indicates creation of a new patient record in a healthcare practice management system (Cliniko).
Attacks that exploit this kind of access
create_patient. It is categorised as a Write tool in the Cliniko MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cliniko MCP Server MCP server in PolicyLayer and add a rule for create_patient: 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 Cliniko MCP Server. Nothing to install.
create_patient 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 create_patient 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 create_patient. 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.
create_patient is provided by the Cliniko MCP Server MCP server (yasboop/new-cliniko-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 →