CVE change feed — the CVE records MODIFIED within a time window, so an agent can incrementally maintain a vulnerability view instead of re-scanning. Pass since (YYYY-MM-DD or ISO datetime); until defaults to now (window ≤120 days). Optional keyword/cpe filter. Each result: id, published + lastMod...
AI agents call security.cve-changes 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 is a data retrieval tool querying a vulnerability database (NVD + CISA KEV) with filtering options. It has no side effects—it only reads and returns vulnerability metadata. The read-only nature and informational purpose place it solidly in the Read category with low severity, as misuse would only result in information disclosure about known vulnerabilities, not system compromise or unauthorized access.
From the tool's definition Tool retrieves CVE records that have been MODIFIED within a time window, returning id, published, lastModified, vulnStatus, CVSS score/severity, description, and kevListed status.
Attacks that exploit this kind of access
CVE change feed — the CVE records MODIFIED within a time window, so an agent can incrementally maintain a vulnerability view instead of re-scanning. Pass since (YYYY-MM-DD or ISO datetime); until defaults to now (window ≤120 days). Optional keyword/cpe filter. Each result: id, published + lastModified, vulnStatus, CVSS score/severity, description, and kevListed (now on the CISA Known-Exploited catalog). Newest first. Live NVD + CISA KEV, keyless. Pairs with security.cve for full detail. 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-changes: 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-changes 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-changes 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-changes. 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-changes 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 →