Get ward, admission date, discharge date, and length-of-stay.
AI agents call get_admission_info to retrieve information from MCPDischarge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves Protected Health Information (PHI) related to patient admission records. While the action itself is read-only with no side effects, the severity is elevated to 'high' because: (1) it accesses sensitive PHI in a healthcare context; (2) unauthorized exposure of admission patterns, dates, and ward assignments could enable harm such as stalking, targeting, or privacy violations; (3) the server has…
From the tool's definition Tool name 'get_admission_info' and description stating it retrieves 'ward, admission date, discharge date, and length-of-stay' without mentioning modification, deletion, or external operations indicates a data retrieval operation.
Attacks that exploit this kind of access
Get ward, admission date, discharge date, and length-of-stay. It is categorised as a Read tool in the MCPDischarge MCP Server, which means it retrieves data without modifying state.
Register the MCPDischarge MCP server in PolicyLayer and add a rule for get_admission_info: 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 MCPDischarge. Nothing to install.
get_admission_info 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 get_admission_info 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 get_admission_info. 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.
get_admission_info is provided by the MCPDischarge MCP server (prashantsingh1234/mcp_project). 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 →