Check for food-drug interactions for a specific drug.
AI agents call check_food_drug_interaction to retrieve information from Pharmacy MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a reference database to return food-drug interaction data. It is a read-only informational lookup. Severity is medium because incorrect or missing interaction data could influence clinical decisions, but the tool itself does not modify any data or trigger external actions.
From the tool's definition 'Check for food-drug interactions' — retrieves interaction information for a specific drug; purely a lookup/query operation with no side effects.
Attacks that exploit this kind of access
Check for food-drug interactions for a specific drug. It is categorised as a Read tool in the Pharmacy MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Pharmacy MCP Server MCP server in PolicyLayer and add a rule for check_food_drug_interaction: 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 Pharmacy MCP Server. Nothing to install.
check_food_drug_interaction 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 check_food_drug_interaction 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 check_food_drug_interaction. 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.
check_food_drug_interaction is provided by the Pharmacy MCP Server MCP server (u9401066/pharmacy-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 →