AI agents call get_upload_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 only retrieves a temporary signed URL; it does not itself perform any upload or modification. The actual file upload would be a separate action triggered by the user in a browser. Generating a link is a read operation, though it facilitates a future write.
From the tool's definition Get a temporary upload link...Returns a signed URL that opens a file upload form in the browser.
Attacks that exploit this kind of access
Get a temporary upload link to add a book to the library. Returns a signed URL that opens a file upload form in the browser. The link expires in 10 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_upload_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_upload_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_upload_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_upload_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_upload_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.
get_upload_link is one line of Lyceum's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →