AI agents call pbs_get_tasks 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 queries and displays PBS (Proxmox Backup Server) task history including backup jobs, verify tasks, and garbage collection events. It performs no mutations, deletions, or external operations—only retrieval and display of existing task records. The blast radius of misuse is minimal since an AI agent querying task history cannot damage infrastructure or data.
From the tool's definition Tool name 'pbs_get_tasks' and description 'Show recent PBS task history' indicates a read-only query operation that retrieves historical data without modifying state.
Attacks that exploit this kind of access
Show recent PBS task history: backup jobs, verify tasks, garbage collection, with status and duration. 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 pbs_get_tasks: 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.
pbs_get_tasks 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 pbs_get_tasks 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 pbs_get_tasks. 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.
pbs_get_tasks 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 →