add_hub · Plugwise MCP Server MCP: Risk & Policy

WHAT IT DOES

What add_hub does on Plugwise MCP Server

AI agents use add_hub to create or update resources in Plugwise MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Plugwise MCP Server environment.

WHY IT NEEDS A POLICY

Why add_hub needs a policy

The tool appears to register/add a new Plugwise hub to the management system, which is a reversible write operation (a hub can presumably be removed). The description is mostly about the parameter rather than the action itself, which reduces confidence. Severity is medium because adding an unauthorized hub could expand the attack surface or allow unauthorized device control.

From the tool's definition 'add_hub' - the tool name implies adding/registering a new hub to the system; description mentions hub name/ID used as password and unique identifier

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_hub Rate-limited

add_hub stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_hub": {
      "limits": [
        {
          "counter": "add_hub_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Plugwise MCP Server, so you can run agents against it safely.

FAQ

Questions about add_hub

What does the add_hub tool do? +

The hub name/ID (e.g., glmpuuxg) which is also used as the password. This is the unique identifier found on the back label of your Plugwise hub. It is categorised as a Write tool in the Plugwise MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_hub? +

Register the Plugwise MCP Server MCP server in PolicyLayer and add a rule for add_hub: 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 Plugwise MCP Server. Nothing to install.

What risk level is add_hub? +

add_hub is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_hub? +

Yes. Add a rate_limit block to the add_hub 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.

How do I block add_hub completely? +

Set action: deny in the PolicyLayer policy for add_hub. 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.

What MCP server provides add_hub? +

add_hub is provided by the Plugwise MCP Server MCP server (tommertom/plugwise-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.