AI agents call security.cve-search 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 read-only information retrieval tool that queries a public database (NIST NVD) to find CVE information. It has no side effects, cannot modify data, and cannot execute code or trigger external operations. The worst-case misuse would be information gathering for reconnaissance, which poses minimal risk compared to other categories. Confidence is high because the operation is clearly a database search/lookup.
From the tool's definition Tool searches the NIST NVD for CVEs by product keyword. The description indicates it performs a query/search operation with no modification, deletion, or execution of code. It retrieves publicly available vulnerability data.
Attacks that exploit this kind of access
Find CVEs affecting a product by searching the NIST NVD. Pass product (free-text keyword, e.g. 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-search: 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-search 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-search 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-search. 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-search 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 →