AI agents call get_gene_diseases 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 disease associations for a given gene from public bioinformatics databases (OMIM, etc.). It performs a read-only lookup operation with no side effects, no ability to modify data, and no capability to execute arbitrary operations. The blast radius of misuse is minimal—an agent could retrieve unnecessary disease information but cannot alter data or cause real-world harm.
From the tool's definition Tool name 'get_gene_diseases' and description 'Get genetic diseases associated with a gene from OMIM and other sources' indicate a retrieval operation that queries existing biological databases without modification, deletion, or execution of arbitrary code.
Attacks that exploit this kind of access
Get genetic diseases associated with a gene from OMIM and other sources. 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_gene_diseases: 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_gene_diseases 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_gene_diseases 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_gene_diseases. 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_gene_diseases 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 →