AI agents call get_dosing_guideline to retrieve information from Pgx without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves dosing guidelines from pharmacogenomics reference databases without modifying, executing external operations, or triggering financial transactions. It fits the Read category: queries data with no side effects. Severity is low because incorrect dosing guidance could theoretically cause harm if an AI agent acted on it without human oversight, but the tool itself is passive retrieval.
From the tool's definition Tool name 'get_dosing_guideline' and server context indicating pharmacogenomics analysis with connections to ClinVar, PharmGKB, and other reference databases.
Attacks that exploit this kind of access
get_dosing_guideline. It is categorised as a Read tool in the Pgx MCP Server, which means it retrieves data without modifying state.
Register the Pgx MCP server in PolicyLayer and add a rule for get_dosing_guideline: 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 Pgx. Nothing to install.
get_dosing_guideline 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_dosing_guideline 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_dosing_guideline. 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_dosing_guideline is provided by the Pgx MCP server (julius-schmidt/mcp-pharmacogenomics). 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 →