check_cve
AI agents call check_cve to retrieve information from MCP Server Foundation Template without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to retrieve CVE data—a read operation with no inherent destructive, financial, or code execution impact. The empty description introduces uncertainty, but the naming strongly indicates a query/lookup function.
From the tool's definition Tool name 'check_cve' suggests querying CVE (Common Vulnerabilities and Exposures) databases for vulnerability information, which is a read-only lookup operation. No description provided to confirm side effects.
Attacks that exploit this kind of access
check_cve. It is categorised as a Read tool in the MCP Server Foundation Template MCP Server, which means it retrieves data without modifying state.
Register the MCP Server Foundation Template MCP server in PolicyLayer and add a rule for check_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 Server Foundation Template. Nothing to install.
check_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 check_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 check_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.
check_cve is provided by the MCP Server Foundation Template MCP server (joeyheath65/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 →