AI agents use set_opds_settings 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.
The tool modifies configuration data (enabling/disabling the OPDS catalog and setting credentials) that directly affects how readers authenticate to and access the book library. This is reversible change without permanent destruction, placing it in Write rather than Destructive.
From the tool's definition Tool description states 'Configure OPDS catalog settings' and explicitly mentions setting 'enabled, username, and/or password' — operations that modify authentication and access controls for the OPDS catalog service.
Attacks that exploit this kind of access
Configure OPDS catalog settings. Set enabled, username, and/or password for OPDS Basic Auth. Reader apps use these credentials to browse and download books. 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 set_opds_settings: 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.
set_opds_settings 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 set_opds_settings 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 set_opds_settings. 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.
set_opds_settings 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 →