This record as markdown: /tools/fistacho-ha-nexus-agent/stop-addon.md
What stop_addon does on Ha Nexus Agent
AI agents invoke stop_addon to trigger actions in Ha Nexus Agent. 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.
Why stop_addon is rated High
Stopping an add-on is an Execute action because it runs/triggers an operation on the smart home system that has real-world effects (e.g., disabling automation, security systems, or other critical services). The effects are not data retrieval (Read), data modification (Write), or permanent deletion (Destructive), but rather a state-changing execution.
From the tool's definition Tool name and description: 'stop_addon' - 'Stop a running add-on.' This triggers an external operation (stopping a service/process) whose effects depend on which add-on is specified as an argument.
Attacks that exploit this kind of access
The rule that runs stop_addon safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ha Nexus Agent, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For stop_addon, this is the rule to start with:
stop_addon 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Ha Nexus Agent, apply this rule, and every stop_addon call is checked against it from then on.
Questions about stop_addon
Stop a running add-on. It is categorised as a Execute tool in the Ha Nexus Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ha Nexus Agent MCP server in PolicyLayer and add a rule for stop_addon: 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 Ha Nexus Agent. Nothing to install.
stop_addon 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 stop_addon 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 stop_addon. 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.
stop_addon is provided by the Ha Nexus Agent MCP server (fistacho/ha-nexus-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ha Nexus Agent, and thousands of servers like it.
Across the catalogue