Look up a CVE by id (e.g. CVE-2021-44228) across three authoritative vulnerability feeds in one call: the canonical record (description, CVSS base score + severity + vector, CWE ids, dates, references), whether it is on the US CISA Known Exploited Vulnerabilities catalog (with remediation due dat...
AI agents call security.cve to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs vulnerability database lookups only—a classic read operation that queries multiple authoritative vulnerability feeds and returns structured data about known CVEs. There are no side effects: no data is modified, deleted, executed, or financially committed. The tool is intended for vulnerability triage and anti-hallucination support, which is a pure information-retrieval use case.
From the tool's definition Tool description explicitly states it 'Look[s] up a CVE by id' and retrieves 'the canonical record (description, CVSS base score + severity + vector, CWE ids, dates, references)', 'whether it is on the US CISA Known Exploited Vulnerabilities catalog', and…
Attacks that exploit this kind of access
Look up a CVE by id (e.g. CVE-2021-44228) across three authoritative vulnerability feeds in one call: the canonical record (description, CVSS base score + severity + vector, CWE ids, dates, references), whether it is on the US CISA Known Exploited Vulnerabilities catalog (with remediation due date + known-ransomware flag), and its EPSS exploit-probability score + percentile. The exploited and EPSS sections degrade independently. 404 if unknown. For vulnerability triage, prioritization, and anti-hallucination. Sources: NIST NVD, CISA KEV, FIRST.org EPSS. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for security.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 Mcp. Nothing to install.
security.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 security.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 security.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.
security.cve is provided by the MCP server (@2sio/mcp). 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 →