Check and flag if a drug is a controlled substance.
AI agents call flag_controlled_substance 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 performs a read-only classification check against a drug database. It returns information about whether a substance is controlled, which is a data retrieval operation with no side effects, no code execution, and no destructive or financial impact. The action is informational only, supporting clinical decision-making without executing changes to systems or data.
From the tool's definition Tool name 'flag_controlled_substance' and description 'Check and flag if a drug is a controlled substance' indicate a lookup/query operation that retrieves metadata about drug classification without modifying data, triggering external actions, or moving funds.
Attacks that exploit this kind of access
Check and flag if a drug is a controlled substance. 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 flag_controlled_substance: 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.
flag_controlled_substance 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 flag_controlled_substance 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 flag_controlled_substance. 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.
flag_controlled_substance 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 →