List all drugs currently in stock (no patient ID required).
AI agents call list_in_stock_drugs 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 pharmacy inventory information—a straightforward read operation. While it provides pharmaceutical data, the lack of patient information and the passive nature of the operation (listing stock levels) means misuse poses minimal blast radius.
From the tool's definition Tool name 'list_in_stock_drugs' and description 'List all drugs currently in stock (no patient ID required)' indicate a query operation that retrieves inventory data without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
List all drugs currently in stock (no patient ID required). 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 list_in_stock_drugs: 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.
list_in_stock_drugs 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 list_in_stock_drugs 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 list_in_stock_drugs. 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.
list_in_stock_drugs 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 →