nci_intervention_searcher
AI agents call nci_intervention_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.
The tool searches for cancer intervention information from an authoritative biomedical database. Search operations retrieve data without modifying it, making this a Read category tool. No side effects, reversibility concerns, or financial implications apply. Severity is low because unauthorized searches of medical databases pose minimal direct harm—they return information only without enabling destructive actions.
From the tool's definition Tool name 'nci_intervention_searcher' indicates a search function querying NCI (National Cancer Institute) intervention data.
Attacks that exploit this kind of access
nci_intervention_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 nci_intervention_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.
nci_intervention_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 nci_intervention_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 nci_intervention_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.
nci_intervention_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 →