AI agents call get_download_link to retrieve information from Lyceum without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a temporary download link for an existing book file without modifying, deleting, or executing any operations. It is a read-only query operation. The temporary nature of the link (5-minute expiration) and the fact that it merely returns a URL further reduces the risk profile. The blast radius is minimal—an agent could only access book files the server already permits downloads for.
From the tool's definition Tool description states it 'Get[s] a temporary download link for a book file' and 'Returns a signed URL'. The operation is retrieval-only with no modification or deletion of data.
Attacks that exploit this kind of access
Get a temporary download link for a book file. Returns a signed URL that expires in 5 minutes. It is categorised as a Read tool in the Lyceum MCP Server, which means it retrieves data without modifying state.
Register the Lyceum MCP server in PolicyLayer and add a rule for get_download_link: 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.
get_download_link 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_download_link 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_download_link. 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_download_link 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 →