Generate a complete pharmacogenomic report with all your genes, phenotypes, and affected medication categories.
AI agents call full_pgx_report to retrieve information from Openpgx without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation: it queries and aggregates pharmacogenomic data already in the user's profile. While the output involves sensitive health/genetic information (which elevates severity to medium due to privacy and potential misuse risks), the fundamental operation is data retrieval with no side effects. The 'privacy-first local execution' context reinforces this is query-based analysis.
From the tool's definition The tool 'generates' and 'reports' data from existing genetic profiles without modifying them. The description states it returns 'all your genes, phenotypes, and affected medication categories' — retrieving and aggregating existing data.
Documented attack patterns abuse exactly the kind of access full_pgx_report gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Openpgx, and nothing reaches the server without passing your rules. This is the rule we recommend for full_pgx_report:
{
"version": "1",
"default": "deny",
"tools": {
"full_pgx_report": {}
}
}full_pgx_report is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Generate a complete pharmacogenomic report with all your genes, phenotypes, and affected medication categories. It is categorised as a Read tool in the Openpgx MCP Server, which means it retrieves data without modifying state.
Register the Openpgx MCP server in PolicyLayer and add a rule for full_pgx_report: 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 Openpgx. Nothing to install.
full_pgx_report 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 full_pgx_report 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 full_pgx_report. 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.
full_pgx_report is provided by the Openpgx MCP server (open-pgx/openpgx). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Openpgx, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
15 Openpgx tools catalogued and risk-classified — across an index of 43,000+ MCP servers.