Retrieves entities (or devices) of certain types — cameras, doorbell cameras, badge readers, access-controlled doors, audio gateways, door sensors, environmental sensors, motion sensors, buttons, keypads, environmental gateways. Can request multiple entity types at once. The return structure is a...
Part of the Rhombus Node server.
Free to start. No card required.
AI agents call get-entity-tool to retrieve information from Rhombus Node without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get-entity-tool only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"get-entity-tool": {}
}
} See the full Rhombus Node policy for all 31 tools.
These attack patterns abuse exactly the kind of access get-entity-tool gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Retrieves entities (or devices) of certain types — cameras, doorbell cameras, badge readers, access-controlled doors, audio gateways, door sensors, environmental sensors, motion sensors, buttons, keypads, environmental gateways. Can request multiple entity types at once. The return structure is a JSON string that contains the states (including names, UUIDs, location, model, firmware, connection status) of the requested entities. This data is exact. Primary use cases: 1. Looking up a device by name. When the user mentions a specific camera, door, sensor, etc. by name (e.g. "describe camera 1919 Front Door Entrance", "what's the status of HW Lab door"), call this tool with the matching entityType, scan the returned list, and fuzzy/case-insensitive substring match the user's reference against the name field. Don't ask the user to clarify — try this lookup first, and only ask if there are genuinely multiple plausible matches in the results. 2. Listing all devices of a type (cameras, doors, sensors, etc.) for a location or org-wide. 3. Checking device health and connectivity. Each device includes a connected boolean (true = online, false = offline). For "which devices are offline?" / "is X online?" / health questions, fetch the relevant entityTypes and inspect connected. When the user asks to "describe", "look up", "find", "show me", or "tell me about" a named device, this is almost always the right starting tool — call it before asking the user for more specifics.. It is categorised as a Read tool in the Rhombus Node MCP Server, which means it retrieves data without modifying state.
Register the Rhombus Node MCP server in PolicyLayer and add a rule for get-entity-tool: 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 Rhombus Node. Nothing to install.
get-entity-tool 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 get-entity-tool 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 get-entity-tool. 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.
get-entity-tool is provided by the Rhombus Node MCP server (rhombus-node-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 31 Rhombus Node tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.