AI agents call get_network_devices to retrieve information from Homelab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only retrieval of network device inventory from Unifi infrastructure. It gathers device status and configuration information but does not modify, execute commands on, or delete any network devices. The caching mechanism further confirms it is a passive query operation.
From the tool's definition Tool retrieves Unifi network devices with 'status and basic info'; the description explicitly states 'Get all' and includes caching optimization, indicating a query operation with no side effects.
Attacks that exploit this kind of access
Get all Unifi network devices (switches, APs, gateways) with status and basic info. This is cached for better performance. It is categorised as a Read tool in the Homelab MCP Server, which means it retrieves data without modifying state.
Register the Homelab MCP server in PolicyLayer and add a rule for get_network_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 Homelab. Nothing to install.
get_network_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 get_network_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 get_network_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.
get_network_devices is provided by the Homelab MCP server (myraffy/homelab-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 →