AI agents call calculate_prs to retrieve information from Gwas without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
PRS calculation is a standard bioinformatics analysis that retrieves and processes existing data to produce computed results. It does not create, modify, delete data, execute arbitrary code, move funds, or trigger irreversible actions. The output is a calculated score, not a state change. The tool sits alongside other analytical functions (pca, heritability, inflation) all of which are computational reads.
From the tool's definition calculate_prs computes derived metrics (Polygenic Risk Scores) from GWAS summary statistics and target genotypes—a read-only analytical operation that performs calculations without modifying data or triggering external side effects.
Attacks that exploit this kind of access
Calculate Polygenic Risk Scores (PRS) for individuals using GWAS summary statistics and target genotypes. It is categorised as a Read tool in the Gwas MCP Server, which means it retrieves data without modifying state.
Register the Gwas MCP server in PolicyLayer and add a rule for calculate_prs: 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 Gwas. Nothing to install.
calculate_prs 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 calculate_prs 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 calculate_prs. 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.
calculate_prs is provided by the Gwas MCP server (muslus/gwas-mcp). 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 →