Update an existing shelf
AI agents use update_shelf to create or update resources in BookStack MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your BookStack MCP Server environment.
This tool modifies existing shelf metadata or properties (name, description, books contained) but does not irreversibly delete data or execute arbitrary commands. It is categorized as Write because updates are reversible—the previous shelf state can be restored by updating again with different values.
From the tool's definition Tool name 'update_shelf' and description 'Update an existing shelf' indicate modification of existing data. BookStack shelves are reversible organizational containers for books.
Attacks that exploit this kind of access
Update an existing shelf. It is categorised as a Write tool in the BookStack MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the BookStack MCP Server MCP server in PolicyLayer and add a rule for update_shelf: 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 BookStack MCP Server. Nothing to install.
update_shelf 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 update_shelf 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 update_shelf. 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.
update_shelf is provided by the BookStack MCP Server MCP server (lautarobarba/bookstack_mcp_server). 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 →