AI agents call get_all_pages to retrieve information from Wikijs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a retrieval/query operation that returns information about existing pages without modifying, deleting, or executing any external operations. It is analogous to a list or fetch action. The blast radius of misuse is minimal—an agent could enumerate pages but cannot modify or delete content. Severity is low because WikiJS page metadata is typically non-sensitive, and the operation is read-only.
From the tool's definition Tool name is 'get_all_pages' and description states 'Get all pages in WikiJS' — this retrieves/lists data with no side effects.
Attacks that exploit this kind of access
Get all pages in WikiJS. It is categorised as a Read tool in the Wikijs MCP Server, which means it retrieves data without modifying state.
Register the Wikijs MCP server in PolicyLayer and add a rule for get_all_pages: 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 Wikijs. Nothing to install.
get_all_pages is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_all_pages 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 get_all_pages. 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.
get_all_pages is provided by the Wikijs MCP server (wikijs-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 →