AI agents call get_drug_targets 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.
This tool performs a simple lookup/query of existing drug target information from a public bioinformatics database (Open Targets). It retrieves and presents data about drugs associated with a gene with no side effects, data modification, code execution, or external operations. This is a standard Read category operation.
From the tool's definition Tool name 'get_drug_targets' and description states it 'shows drugs in development and approved drugs targeting this gene' — a retrieval operation querying Open Targets database without modifying data or triggering external actions.
Attacks that exploit this kind of access
Get drug target information from Open Targets for a gene. Shows drugs in development and approved drugs targeting this gene. 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 get_drug_targets: 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.
get_drug_targets 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_drug_targets 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_drug_targets. 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_drug_targets 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 →