AI agents call proxmox_get_logs 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 retrieves log data from VMs or containers for inspection and analysis purposes. It has no side effects—it does not create, modify, delete, or execute any operations on the infrastructure. The blast radius of misuse is minimal: an agent could only read logs that already exist, potentially exposing sensitive information in those logs but not affecting system state or operations.
From the tool's definition Tool name 'proxmox_get_logs' and description 'Retrieve the last N log lines' indicate a read-only operation that queries historical log data without modifying, executing commands on, or deleting infrastructure.
Attacks that exploit this kind of access
Retrieve the last N log lines from a VM or LXC container (default 100 lines). 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 proxmox_get_logs: 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.
proxmox_get_logs 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 proxmox_get_logs 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 proxmox_get_logs. 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.
proxmox_get_logs 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 →