AI agents call get_disease_associations 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 retrieves information from a biological database (Open Targets) without creating, modifying, or deleting data. It performs a query operation to fetch pre-computed disease association data and evidence scores for a given gene. This is a classic Read operation with minimal blast radius if misused—it can only disclose information already in the public database.
From the tool's definition Tool name and description indicate 'Get disease associations' which is a query/retrieval operation. The description states it retrieves associations 'from Open Targets with evidence scores' - a read-only lookup with no modification of underlying data.
Attacks that exploit this kind of access
Get disease associations for a gene from Open Targets with evidence scores. 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_disease_associations: 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_disease_associations 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_disease_associations 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_disease_associations. 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_disease_associations 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 →