Get a proxy host by ID.
AI agents call npm_get_proxy_host to retrieve information from Nginx Manager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward retrieval operation that queries and returns information about a proxy host configuration. It has no destructive, write, execute, or financial implications. The only risk is information disclosure if sensitive proxy host details are exposed, which is a low severity concern in a typical infrastructure management context.
From the tool's definition Tool name 'npm_get_proxy_host' and description 'Get a proxy host by ID' indicate retrieval of data without modification or side effects.
Attacks that exploit this kind of access
Get a proxy host by ID. It is categorised as a Read tool in the Nginx Manager MCP Server, which means it retrieves data without modifying state.
Register the Nginx Manager MCP server in PolicyLayer and add a rule for npm_get_proxy_host: 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 Nginx Manager. Nothing to install.
npm_get_proxy_host 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 npm_get_proxy_host 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 npm_get_proxy_host. 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.
npm_get_proxy_host is provided by the Nginx Manager MCP server (kognar-ai/ngnix-manager-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 →