AI agents call openemr_visit_prep to retrieve information from Openemr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and synthesizes patient clinical data to produce a summary document. While the output is sensitive healthcare information (high severity due to PHI exposure and potential patient harm if data is inaccurate), the tool itself performs a read operation with no side effects on the medical record.
From the tool's definition Tool generates a pre-visit clinical brief by aggregating patient data (top risks, medication safety, care gaps). The description states it retrieves and organizes existing information without modifying records ('Generate a...brief','no hallucination').
Attacks that exploit this kind of access
Generate a pre-visit clinical brief for a patient: top risks, medication safety, care gaps, and suggested agenda. Evidence-linked, no hallucination. It is categorised as a Read tool in the Openemr MCP Server, which means it retrieves data without modifying state.
Register the Openemr MCP server in PolicyLayer and add a rule for openemr_visit_prep: 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 Openemr. Nothing to install.
openemr_visit_prep 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 openemr_visit_prep 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 openemr_visit_prep. 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.
openemr_visit_prep is provided by the Openemr MCP server (shruti-jn/openemr-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 →