AI agents use set_custom_column to create or update resources in Calibre — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Calibre environment.
This tool creates or modifies custom column definitions in a Calibre library—a Write operation since custom columns can be deleted or updated later. Severity is medium because misconfiguration could affect library organization, but changes are reversible. Confidence is 0.85 because the tool description is empty, requiring inference from the name and server context.
From the tool's definition Tool name 'set_custom_column' indicates modification of metadata fields. Sibling tools include 'set_metadata' which modifies book records, and the server description mentions 'manage metadata'.
Attacks that exploit this kind of access
set_custom_column. It is categorised as a Write tool in the Calibre MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Calibre MCP server in PolicyLayer and add a rule for set_custom_column: 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 Calibre. Nothing to install.
set_custom_column 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_custom_column 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_custom_column. 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_custom_column is provided by the Calibre MCP server (xmkevinchen/calibre-mcp). 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 →