AI agents call homelab_capabilities 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 operation—enumerating or listing available capabilities—with no side effects. It does not create, modify, execute, delete, or move resources. Even if an AI agent misuses it by calling it repeatedly, the blast radius is minimal (information disclosure only). Classification as 'Read' is appropriate.
From the tool's definition Tool name 'homelab_capabilities' and description 'List all available homelab tools grouped by service domain' indicate a query/list operation that retrieves information about available tools without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
List all available homelab tools grouped by service domain. 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 homelab_capabilities: 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.
homelab_capabilities 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 homelab_capabilities 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 homelab_capabilities. 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.
homelab_capabilities is provided by the Homelab MCP server (nainounen/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 →