Update metadata fields on a book in the library. Fields can include: title, authors (as array), tags (as array), series, publisher, rating, comments, read_at (ISO date string to mark when read, or null to clear), etc.
AI agents use set_metadata 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 modifies metadata reversibly without deleting data or executing arbitrary code. Users could change book information (title, authors, tags, series, publisher, rating, comments, read status), which constitutes Write-class behavior.
From the tool's definition Tool description states 'Update metadata fields on a book' - the verb 'Update' indicates modification of existing data. Accepts multiple field types (title, authors, tags, series, publisher, rating, comments, read_at) that can be changed.
Attacks that exploit this kind of access
Update metadata fields on a book in the library. Fields can include: title, authors (as array), tags (as array), series, publisher, rating, comments, read_at (ISO date string to mark when read, or null to clear), etc. 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_metadata: 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_metadata 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_metadata 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_metadata. 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_metadata 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 →