AI agents invoke send_url_to_device to trigger actions in Lyceum. 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 performs multiple chained operations: fetching a URL, converting content, and pushing it to an external device. It triggers an external operation (sending to a device) whose effects depend on arguments. It doesn't merely read or write library data, nor is it destructive or financial — it executes a workflow that interacts with an external e-reader device.
From the tool's definition Fetch a URL, convert the article to an epub, and send it directly to an e-reader device without saving to the library
Attacks that exploit this kind of access
Fetch a URL, convert the article to an epub, and send it directly to an e-reader device without saving to the library. It is categorised as a Execute tool in the Lyceum MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Lyceum MCP server in PolicyLayer and add a rule for send_url_to_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.
send_url_to_device 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 send_url_to_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 send_url_to_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.
send_url_to_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 →