AI agents call search_host_vulns to retrieve information from Yamory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries vulnerability data from the yamory vulnerability management system. It performs a read-only search operation that returns information about detected host vulnerabilities. There are no side effects, no data modification, and no external execution or financial impact. Results are scoped to the configured team, limiting exposure.
From the tool's definition Tool name is 'search_host_vulns' and description states it 'Search host vulnerabilities' and 'Returns triage level, status, affected host/package, solution, and advisory information.' The verb 'Search' and 'Returns' indicate data retrieval with no…
Attacks that exploit this kind of access
Search host vulnerabilities detected by yamory. Returns triage level, status, affected host/package, solution, and advisory information. Results are scoped to the configured team. It is categorised as a Read tool in the Yamory MCP Server, which means it retrieves data without modifying state.
Register the Yamory MCP server in PolicyLayer and add a rule for search_host_vulns: 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 Yamory. Nothing to install.
search_host_vulns 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_host_vulns 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_host_vulns. 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_host_vulns is provided by the Yamory MCP server (@aranseshita/yamory-mcp-server). 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 →