Flag a mismatch between prescribed dose and formulary standard dose.
AI agents call detect_dose_conflict 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 validation/detection tool that retrieves and compares data (prescribed dose vs. formulary standards) to identify discrepancies. It has no side effects—it does not execute prescriptions, modify medication records, execute commands, or delete anything. It is purely informational flagging.
From the tool's definition Tool detects and flags dose conflicts by comparing prescribed dose against formulary standards. The verb 'flag' indicates identification and reporting of a mismatch without modifying prescriptions, inventory, or patient records.
Attacks that exploit this kind of access
Flag a mismatch between prescribed dose and formulary standard dose. 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 detect_dose_conflict: 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.
detect_dose_conflict 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 detect_dose_conflict 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 detect_dose_conflict. 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.
detect_dose_conflict 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 →