AI agents call vul_cve_search to retrieve information from Cve Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only lookup of CVE information by ID. It retrieves and returns structured data without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal—an agent could only access publicly available CVE records.
From the tool's definition Tool description states it retrieves 'a JSON of a specific CVE ID' — a pure query operation with no modifications or side effects. The server is explicitly described as 'querying the CVE-Search API' for retrieving vulnerability data.
Documented attack patterns abuse exactly the kind of access vul_cve_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cve Search, and nothing reaches the server without passing your rules. This is the rule we recommend for vul_cve_search:
{
"version": "1",
"default": "deny",
"tools": {
"vul_cve_search": {}
}
}vul_cve_search 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.
To get a JSON of a specific CVE ID. It is categorised as a Read tool in the Cve Search MCP Server, which means it retrieves data without modifying state.
Register the Cve Search MCP server in PolicyLayer and add a rule for vul_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 Cve Search. Nothing to install.
vul_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 vul_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 vul_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.
vul_cve_search is provided by the Cve Search MCP server (roadwy/cve-search_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Cve Search tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 Cve Search tools catalogued and risk-classified — across an index of 42,500+ MCP servers.