cve_config
AI agents call cve_config to retrieve information from CVE Risk MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on context, cve_config most likely retrieves or displays configuration related to CVE lookups (e.g., data sources, filtering preferences, or assessment parameters). No evidence suggests it modifies data, executes code, deletes records, or moves money. The empty description and inference from sibling tools lower confidence, but the Read category is the safest assignment.
From the tool's definition Tool name 'cve_config' and empty description provide minimal direct evidence. Inferred from sibling tools (cve_lookup, cve_rank, cve_status, cve_export) which are all read-only lookups of CVE and vulnerability data.
Attacks that exploit this kind of access
cve_config. It is categorised as a Read tool in the CVE Risk MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CVE Risk MCP Server MCP server in PolicyLayer and add a rule for cve_config: 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 Risk MCP Server. Nothing to install.
cve_config 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 cve_config 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 cve_config. 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.
cve_config is provided by the CVE Risk MCP Server MCP server (sarveshkapre/cve-risk-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 →