Triage CVEs with EPSS scores, CVSS severity, and KEV status. Note: makes individual NVD API calls per CVE; expect ~6s/CVE without API key.
AI agents call triage_cve 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.
The tool reads and aggregates vulnerability data from NVD to enrich CVE information for decision-making. It has no write, delete, execute, or financial side effects. Severity is medium rather than low because CVE data informs security decisions, and an agent could be misled by incorrect or manipulated triage results, but the tool itself only retrieves information without executing code or triggering external actions…
From the tool's definition Tool performs triaging/assessment of CVEs by querying external vulnerability data sources (NVD API) and retrieving EPSS scores, CVSS severity, and KEV status.
Documented attack patterns abuse exactly the kind of access triage_cve 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 triage_cve:
{
"version": "1",
"default": "deny",
"tools": {
"triage_cve": {}
}
}triage_cve 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.
Triage CVEs with EPSS scores, CVSS severity, and KEV status. Note: makes individual NVD API calls per CVE; expect ~6s/CVE without API key. 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 triage_cve: 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.
triage_cve 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 triage_cve 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 triage_cve. 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.
triage_cve 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.