AI agents use wiki_create_page to create or update resources in Wiki Js — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wiki Js environment.
Creating a new wiki page is a Write operation: it modifies the wiki state by adding content, but the action is reversible (the page can be deleted or its content modified later). The blast radius is medium because an agent could create numerous spam or misleading pages, but the damage is containable through page deletion or rollback mechanisms typical in wiki systems.
From the tool's definition Tool name is 'wiki_create_page' and description states 'Create a new wiki page' — this is a create operation that adds new data to the wiki system reversibly.
Attacks that exploit this kind of access
Create a new wiki page at the given path with markdown content. It is categorised as a Write tool in the Wiki Js MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wiki Js MCP server in PolicyLayer and add a rule for wiki_create_page: 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 Wiki Js. Nothing to install.
wiki_create_page 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 wiki_create_page 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 wiki_create_page. 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.
wiki_create_page is provided by the Wiki Js MCP server (osianet/wiki-js-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 →