Pull spring (for locks with auto-pull disabled)
AI agents invoke pull_spring to trigger actions in Home Controller. 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.
Pulling a spring on a lock is a physical, external operation that unlocks a door or access point. While it could be argued as reversible (the lock can be re-engaged), the primary concern is that it triggers a real-world security action — opening a lock — which has significant safety and security implications. It fits Execute because it triggers an external physical operation.
From the tool's definition 'Pull spring (for locks with auto-pull disabled)' — this triggers a physical actuator on a lock mechanism, releasing or opening a lock in the real world.
Attacks that exploit this kind of access
Pull spring (for locks with auto-pull disabled). It is categorised as a Execute tool in the Home Controller MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Home Controller MCP server in PolicyLayer and add a rule for pull_spring: 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 Home Controller. Nothing to install.
pull_spring 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 pull_spring 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 pull_spring. 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.
pull_spring is provided by the Home Controller MCP server (winsthuang/home-controller). 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 →