AI agents call search_by_severity to retrieve information from Nvd Cve without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing CVE data from the NVD API based on severity filters. It has no side effects, does not create, modify, or delete data, and does not execute arbitrary code. It is a straightforward data retrieval operation and therefore classified as Read.
From the tool's definition Tool description states it "Filter[s] CVEs by severity" and is part of a server that provides tools to "search, filter, and retrieve CVE data" with no indication of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Filter CVEs by severity (CRITICAL, HIGH, MEDIUM, LOW). It is categorised as a Read tool in the Nvd Cve MCP Server, which means it retrieves data without modifying state.
Register the Nvd Cve MCP server in PolicyLayer and add a rule for search_by_severity: 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 Nvd Cve. Nothing to install.
search_by_severity 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_by_severity 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_by_severity. 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_by_severity is provided by the Nvd Cve MCP server (millsks/nvd-cve-mcp-server). 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 →