AI agents invoke set_lock_state to trigger actions in Nuki. 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.
This tool controls a physical smart lock, either locking or unlocking a door. While it is technically reversible (you can re-lock or re-unlock), the real-world consequences of misuse are critical: an attacker or misbehaving agent could unlock a door, granting unauthorized physical access to a home or premises.
From the tool's definition 'Lock or unlock a Nuki device' — triggers a physical external operation (engaging or disengaging a door lock mechanism)
Attacks that exploit this kind of access
Lock or unlock a Nuki device. It is categorised as a Execute tool in the Nuki MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nuki MCP server in PolicyLayer and add a rule for set_lock_state: 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 Nuki. Nothing to install.
set_lock_state 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 set_lock_state 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 set_lock_state. 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.
set_lock_state is provided by the Nuki MCP server (sandraschi/nuki-mcp). 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 →