AI agents call get_variant_frequency 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 population genetics data about variant frequencies—a read-only lookup with no side effects. The 'get_' prefix and pharmacogenomics context confirm it queries existing data. Even if misused by an AI agent, it cannot modify, delete, or execute arbitrary operations; it only returns informational statistics used for clinical decision-support.
From the tool's definition Tool name 'get_variant_frequency' indicates a retrieval operation; sibling tools on this pharmacogenomics server are all read-only queries (lookup_variant_clinvar, get_dosing_guideline, search_gene_variants_clinvar, etc.).
Attacks that exploit this kind of access
get_variant_frequency. 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_variant_frequency: 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_variant_frequency 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_variant_frequency 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_variant_frequency. 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_variant_frequency 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 →