Connects to a nomos controller by name. Disconnects from any previously connected controller. After connecting, all tools, resources, and prompts from that controller become available.
AI agents invoke select_controller to trigger actions in nomos MCP Bridge. 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 triggers an external operation: it disconnects from one controller and connects to another, changing the active system state. This is not a simple read or write of data — it switches the operational context of a smart home controller, which can expose new tools and capabilities.
From the tool's definition 'Connects to a nomos controller by name. Disconnects from any previously connected controller. After connecting, all tools, resources, and prompts from that controller become available.'
Attacks that exploit this kind of access
Connects to a nomos controller by name. Disconnects from any previously connected controller. After connecting, all tools, resources, and prompts from that controller become available. It is categorised as a Execute tool in the nomos MCP Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the nomos MCP Bridge MCP server in PolicyLayer and add a rule for select_controller: 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 nomos MCP Bridge. Nothing to install.
select_controller 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 select_controller 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 select_controller. 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.
select_controller is provided by the nomos MCP Bridge MCP server (nomos-system/nomos-mcp-bridge). 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 →