Search for devices by hostname, IP, or MAC address.
AI agents call search_devices to retrieve information from UniFi MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries device information based on search criteria. It has no side effects, does not modify network state, and does not execute commands or operations. It is purely informational, similar to the sibling tool 'list_devices'. The blast radius of misuse is minimal—an attacker could discover devices on the network but cannot directly harm infrastructure, move money, or permanently delete data.
From the tool's definition Tool name 'search_devices' and description 'Search for devices by hostname, IP, or MAC address' indicate a query/retrieval operation with no modification of data.
Attacks that exploit this kind of access
Search for devices by hostname, IP, or MAC address. It is categorised as a Read tool in the UniFi MCP Server MCP Server, which means it retrieves data without modifying state.
Register the UniFi MCP Server MCP server in PolicyLayer and add a rule for search_devices: 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 UniFi MCP Server. Nothing to install.
search_devices 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_devices 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_devices. 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_devices is provided by the UniFi MCP Server MCP server (nathan-bw/unifi-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 →