AI agents call list_scenes to retrieve information from HueMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves scene data from the Hue bridge using the CLIP v2 API. It performs a read-only query operation filtered optionally by group_id (room or zone). There are no side effects, state changes, or external operations triggered. The minimal blast radius of misuse (an agent listing available scenes) poses negligible security risk.
From the tool's definition Tool name is 'list_scenes' and description states 'List scenes', which retrieves or queries scene information without modifying any state.
Attacks that exploit this kind of access
List scenes. If group_id is given (a room or zone id), only scenes targeting. It is categorised as a Read tool in the HueMCP MCP Server, which means it retrieves data without modifying state.
Register the Hue MCP server in PolicyLayer and add a rule for list_scenes: 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 HueMCP. Nothing to install.
list_scenes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_scenes 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 list_scenes. 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.
list_scenes is provided by the Hue MCP server (mbruton/huemcp). 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 →