search_kev
AI agents call search_kev to retrieve information from Risky Business MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches a vulnerability database for known exploited vulnerabilities, which is a query/retrieval operation with no side effects. Even though the data relates to security exploits, the tool itself only reads and returns information from an external catalog. The misuse risk is low because searching vulnerability databases cannot directly harm systems; it only gathers threat intelligence.
From the tool's definition Tool name 'search_kev' indicates searching CISA's Known Exploited Vulnerabilities (KEV) catalog. The server description explicitly states it 'accessing CISA's Known Exploited Vulnerabilities catalog' and 'threat intelligence gathering', which are read-only…
Attacks that exploit this kind of access
search_kev. It is categorised as a Read tool in the Risky Business MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Risky Business MCP Server MCP server in PolicyLayer and add a rule for search_kev: 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 Risky Business MCP Server. Nothing to install.
search_kev 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 search_kev 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 search_kev. 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.
search_kev is provided by the Risky Business MCP Server MCP server (khizar-anjum/risky-business-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 →