Get all possible therapeutic alternatives for a drug.
AI agents call get_all_alternatives 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.
The tool performs a read-only retrieval of therapeutic alternative information. It queries a drug database to return lookup results. No data is created, modified, deleted, or committed. No external operations or code execution is triggered. The worst-case misuse would be information gathering, which poses minimal risk in a hospital discharge coordination context.
From the tool's definition Tool is named 'get_all_alternatives' and described as 'Get all possible therapeutic alternatives for a drug.' This is a query/lookup operation that retrieves reference data about pharmaceutical alternatives without modifying, deleting, or executing external…
Attacks that exploit this kind of access
Get all possible therapeutic alternatives for a drug. 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 get_all_alternatives: 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.
get_all_alternatives 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 get_all_alternatives 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 get_all_alternatives. 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.
get_all_alternatives 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 →