Fetch detailed information for a specific CVE from the live NVD database.
AI agents call get_cve_detail to retrieve information from Security Framework without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves vulnerability metadata from a public database without creating, modifying, deleting, or executing any operations. It has no side effects beyond data retrieval and serves an informational purpose for security research and compliance mapping.
From the tool's definition Tool fetches detailed information for a specific CVE from the live NVD database. Keywords: 'Fetch' and 'detailed information' indicate retrieval without modification or execution. The NVD (National Vulnerability Database) is a read-only public data source.
Documented attack patterns abuse exactly the kind of access get_cve_detail gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Security Framework, and nothing reaches the server without passing your rules. This is the rule we recommend for get_cve_detail:
{
"version": "1",
"default": "deny",
"tools": {
"get_cve_detail": {}
}
}get_cve_detail is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Fetch detailed information for a specific CVE from the live NVD database. It is categorised as a Read tool in the Security Framework MCP Server, which means it retrieves data without modifying state.
Register the Security Framework MCP server in PolicyLayer and add a rule for get_cve_detail: 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 Security Framework. Nothing to install.
get_cve_detail 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_cve_detail 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_cve_detail. 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_cve_detail is provided by the Security Framework MCP server (zer0-kr/security-framework-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Security Framework, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
41 Security Framework tools catalogued and risk-classified — across an index of 43,000+ MCP servers.