AI agents use create_knowledge_library to create or update resources in Ai Books — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ai Books environment.
This tool creates a new data structure (knowledge library) but does not delete, execute arbitrary code, or commit financial transactions. Creation of new data structures is a Write-category operation.
From the tool's definition Tool description states it 'Creates a new knowledge library', which is a create operation that modifies data reversibly. The sibling tool 'delete_knowledge_library' confirms libraries can be deleted, reinforcing that creation is reversible.
Attacks that exploit this kind of access
Creates a new knowledge library by compressing text using gravitational memory. It is categorised as a Write tool in the Ai Books MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ai Books MCP server in PolicyLayer and add a rule for create_knowledge_library: 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 Ai Books. Nothing to install.
create_knowledge_library 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 create_knowledge_library 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 create_knowledge_library. 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.
create_knowledge_library is provided by the Ai Books MCP server (nvmtoxic/ai-books-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 →