AI agents call list_pages to retrieve information from Wikimcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only listing operation with no side effects. It allows inspection of the wiki's structure but does not create, modify, delete, or execute any code. The optional subdirectory filtering is a query parameter that narrows results. Classified as Read with low severity because disclosure of wiki page names carries minimal risk in most contexts.
From the tool's definition list_pages with description 'List all wiki pages, optionally filtered to a subdirectory' retrieves and queries page metadata without modifying any data.
Attacks that exploit this kind of access
List all wiki pages, optionally filtered to a subdirectory. It is categorised as a Read tool in the Wikimcp MCP Server, which means it retrieves data without modifying state.
Register the Wiki MCP server in PolicyLayer and add a rule for list_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 Wikimcp. Nothing to install.
list_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 list_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 list_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.
list_pages is provided by the Wiki MCP server (mohith-das/wikimcp). 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 →