Validate prescribed dose against formulary standards.
AI agents call check_dose_validity 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 is a lookup/validation operation that compares a prescribed dose to formulary guidelines. It retrieves information and performs a comparison to inform decision-making, but does not create, modify, delete, or execute any irreversible action. The tool has no side effects on patient records, medication inventory, or billing systems.
From the tool's definition The tool 'validates prescribed dose against formulary standards' — it queries/checks data against reference standards without modifying any records, dispensing medication, or executing clinical actions.
Attacks that exploit this kind of access
Validate prescribed dose against formulary standards. 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 check_dose_validity: 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.
check_dose_validity 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_dose_validity 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_dose_validity. 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_dose_validity 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 →