Download pending system updates. This starts the download process; the system is not updated until update_apply is called.
AI agents invoke update_download to trigger actions in Truenas. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Downloading system updates triggers an external operation (fetching update packages from remote servers) with side effects such as network usage and disk writes. It is not purely reading data, and it modifies the local system state by storing update files. Since the actual update is deferred to update_apply, it is not yet Destructive, making Execute the most appropriate category.
From the tool's definition Download pending system updates. This starts the download process
Documented attack patterns abuse exactly the kind of access update_download gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Truenas, and nothing reaches the server without passing your rules. This is the rule we recommend for update_download:
{
"version": "1",
"default": "deny",
"tools": {
"update_download": {
"limits": [
{
"counter": "update_download_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} update_download stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Download pending system updates. This starts the download process; the system is not updated until update_apply is called. It is categorised as a Execute tool in the Truenas MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Truenas MCP server in PolicyLayer and add a rule for update_download: 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 Truenas. Nothing to install.
update_download is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the update_download 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 update_download. 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.
update_download is provided by the Truenas MCP server (spranab/truenas-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Truenas, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
279 Truenas tools catalogued and risk-classified — across an index of 43,000+ MCP servers.