Start adding an e-reader device. For Boox: params should include email and optionally region (us, eu, or cn, defaults to eu). A verification code will be sent. For Xteink: params should include email and password. Logs in and lists bound devices. For CrossPoint: no params needed (auto-discovers d...
AI agents use add_device to create or update resources in Lyceum — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lyceum environment.
This tool initiates the process of registering/adding an e-reader device to the system. It creates a new device association (Write), potentially authenticates with external services, and may trigger network discovery. It is not purely destructive or financial, but does create a new binding/configuration. Severity is medium since misuse could link unintended devices or expose credentials.
From the tool's definition Start adding an e-reader device... Logs in and lists bound devices... auto-discovers devices via UDP
Attacks that exploit this kind of access
Start adding an e-reader device. For Boox: params should include email and optionally region (us, eu, or cn, defaults to eu). A verification code will be sent. For Xteink: params should include email and password. Logs in and lists bound devices. For CrossPoint: no params needed (auto-discovers devices via UDP) or provide {ip, port} for manual entry. It is categorised as a Write tool in the Lyceum MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lyceum MCP server in PolicyLayer and add a rule for add_device: 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 Lyceum. Nothing to install.
add_device is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_device 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 add_device. 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.
add_device is provided by the Lyceum MCP server (matthewp/lyceum). 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 →