variant_searcher
AI agents call variant_searcher to retrieve information from CzechMedMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the name and server context (genomic/biomedical data access), this tool most likely retrieves or queries variant information from databases like those connected to alphagenome_predictor (a sibling tool). No evidence suggests modification, execution, deletion, or financial operations. The empty description reduces confidence slightly, but the pattern is consistent with Read category tools on this MCP server.
From the tool's definition Tool name 'variant_searcher' suggests querying genetic variants. The empty description limits certainty, but the naming pattern aligns with sibling read-only tools like 'article_searcher' and 'article_getter' on this healthcare database server.
Attacks that exploit this kind of access
variant_searcher. It is categorised as a Read tool in the CzechMedMCP MCP Server, which means it retrieves data without modifying state.
Register the CzechMed MCP server in PolicyLayer and add a rule for variant_searcher: 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 CzechMedMCP. Nothing to install.
variant_searcher 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 variant_searcher 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 variant_searcher. 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.
variant_searcher is provided by the CzechMed MCP server (petrsovadina/czechmedmcp). 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 →