Search for alleles/variants in the Alliance database.
AI agents call search_alleles to retrieve information from AGR MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries genomics data (alleles and variants) from a read-only database without creating, modifying, deleting, or executing any external operations. It is a straightforward data lookup operation with no side effects, fitting the Read category. Genomics research data queries pose minimal security risk.
From the tool's definition Tool name is 'search_alleles' and description states it 'Search[es] for alleles/variants in the Alliance database.' The verb 'search' and 'for' indicate query/retrieval with no modification or execution of external operations.
Attacks that exploit this kind of access
Search for alleles/variants in the Alliance database. It is categorised as a Read tool in the AGR MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AGR MCP Server MCP server in PolicyLayer and add a rule for search_alleles: 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 AGR MCP Server. Nothing to install.
search_alleles 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 search_alleles 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 search_alleles. 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.
search_alleles is provided by the AGR MCP Server MCP server (nuin/agr-mcp-server-js). 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 →