Confirm that medicines have been issued to the patient.
AI agents use confirm_dispense to create or update resources in MCPDischarge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCPDischarge environment.
This tool records/confirms a dispensing event — it creates or modifies a record indicating medicines were issued. This is a Write operation (updating dispense status in EHR/Pharmacy system). It is reversible in principle (the record could be corrected), so it does not rise to Destructive. However, misuse could result in incorrect medication records affecting patient safety, warranting medium severity.
From the tool's definition Confirm that medicines have been issued to the patient
Attacks that exploit this kind of access
Confirm that medicines have been issued to the patient. It is categorised as a Write tool in the MCPDischarge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCPDischarge MCP server in PolicyLayer and add a rule for confirm_dispense: 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.
confirm_dispense is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the confirm_dispense 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 confirm_dispense. 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.
confirm_dispense 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 →