Get list of user registered devices
AI agents call get_user_devices to retrieve information from Red Bee MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation as it retrieves and lists data (registered devices) without modification or side effects. Severity is medium rather than low because device information can reveal user behavior patterns, device types, locations, and is sensitive personal data that could be leveraged for further attacks (e.g., targeting specific device types for exploitation).
From the tool's definition Tool name is 'get_user_devices' and description states 'Get list of user registered devices'. The action is retrieval/query of device information associated with a user account.
Attacks that exploit this kind of access
Get list of user registered devices. It is categorised as a Read tool in the Red Bee MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Red Bee MCP Server MCP server in PolicyLayer and add a rule for get_user_devices: 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 Red Bee MCP Server. Nothing to install.
get_user_devices 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_user_devices 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_user_devices. 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_user_devices is provided by the Red Bee MCP Server MCP server (tamsi/redbee-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 →