// SCAN REPORT

Plugwise

16 tools. 11 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 5 Jul 2026

11 can modify or destroy data

5 read-only

16 tools total

Verified server · catalogue entry verified 05/07/2026 · full schemas captured for 11 of 16 tools

How to control Plugwise ↓

TOOL MAP

What Plugwise exposes to your agents

Read (5) Write / Execute (10) Destructive / Financial (1)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Plugwise costs in tokens

1,581 tokens of tool definitions, loaded on every request

0.8% of a 200k context window

168 heaviest tool: connect

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Plugwise tools

Destructive · Medium delete_notification This tool performs an irreversible deletion operation on gateway notifications. Execute · High reboot_gateway This is an Execute category tool because it triggers an external operation (gateway restart) whose effects depend on context and timing. Execute · High control_switch This tool triggers external physical operations (turning devices on/off) whose effects depend on arguments. Execute · High set_regulation_mode This tool triggers an external physical operation — changing the heating system's regulation mode.

11 of Plugwise's 16 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Plugwise

PolicyLayer is an MCP gateway — it sits between your AI agents and Plugwise, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_notification": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_hub": {
    "limits": [
      {
        "counter": "add_hub_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_all_temperatures": {
    "limits": [
      {
        "counter": "get_all_temperatures_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Plugwise — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON PLUGWISE →

Instant setup, no code required.

FULL CATALOGUE

All 16 Plugwise tools

DESTRUCTIVE 1 tools

Destructive delete_notification Delete the active notification from the Plugwise gateway. Use this to clear system notifications, alerts, or w

EXECUTE 3 tools

Execute control_switch Turn a switch or relay on or off. Works with Plugwise switches, relays, and smart plugs. Use this to control a Execute reboot_gateway Reboot the Plugwise gateway (use with caution). This will restart the gateway, temporarily interrupting all co Execute set_regulation_mode Set the heating regulation mode. Controls the overall heating system behavior. Use "heating" for normal operat

WRITE 7 tools

Write add_hub Add a new Plugwise hub by providing its name (used as password). Scans the network to find the hub and stores Write connect Connect to a Plugwise gateway (Adam, Anna, Smile P1, or Stretch) and retrieve gateway information. If no host Write set_dhw_mode Set the domestic hot water (DHW) heating mode for systems with hot water control. Auto mode follows the schedu Write set_gateway_mode Set the gateway mode (home, away, vacation). This is a system-wide setting that affects all zones and presets. Write set_preset Set the preset mode on a thermostat or zone (e.g., home, away, sleep, vacation). Presets apply predefined temp Write set_temperature Set the temperature setpoint on a thermostat or zone. Supports single setpoint for heating/cooling systems, or Write set_temperature_offset Set the temperature offset (calibration) for a thermostat device. This adjusts the measured temperature by a f

READ 5 tools

Read get_all_temperatures Get current temperatures and setpoints for all thermostats and zones in the system. Returns comprehensive temp Read get_devices Retrieve all Plugwise devices and their current states, sensors, and capabilities. Returns comprehensive infor Read get_temperature Get current room temperature and setpoint for a specific thermostat or zone. Returns both the measured tempera Read get_temperature_offset Get the temperature offset (calibration) for a thermostat device. The offset is used to calibrate the temperat Read list_hubs List all registered Plugwise hubs from the /hubs folder and in-memory registry. Returns hub information includ

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Plugwise

Can an AI agent delete data through the Plugwise MCP server? +

Yes. The Plugwise server exposes 1 destructive tools including delete_notification. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Plugwise? +

The Plugwise server has 7 write tools including add_hub, connect, set_dhw_mode. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Plugwise.

How many tools does the Plugwise MCP server expose? +

16 tools across 4 categories: Destructive, Execute, Read, Write. 5 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on Plugwise? +

Register the Plugwise MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Plugwise tool call.

Deterministic rules across all 16 Plugwise tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PLUGWISE →

Instant setup, no code required.

16 Plugwise tools catalogued and risk-classified — across an index of 43,000+ MCP servers.