AI agents call openemr_patient_search 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 retrieves patient information without modifying, executing operations on, or deleting data. It is a read-only query function. While it accesses sensitive healthcare data (PHI), the low severity reflects that the tool itself cannot cause irreversible harm—severity depends on the sensitivity of the data exposed and access controls, not the tool's capability.
From the tool's definition Tool description states it 'Search[es] OpenEMR patients by name' and 'Returns matching patient records with ID, DOB, sex, and city.' The verb 'Search' and 'Returns' indicate query/retrieval with no modification of data.
Attacks that exploit this kind of access
Search OpenEMR patients by name. Returns matching patient records with ID, DOB, sex, and city. 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_patient_search: 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_patient_search 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_patient_search 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_patient_search. 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_patient_search 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 →