AI agents call cwiki_get_page to retrieve information from CwikiMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a straightforward data retrieval operation with no side effects, modifications, deletions, or external operations. It queries and returns existing wiki page content. The read-only nature of the server and fetch operation clearly indicate this is a Read category risk with minimal severity.
From the tool's definition Tool description states 'Fetch a wiki page' and server is explicitly described as 'Read-only MCP server'. The tool retrieves content by page title or ID with no modification capabilities.
Attacks that exploit this kind of access
Fetch a wiki page by page title or page id. It is categorised as a Read tool in the CwikiMCP MCP Server, which means it retrieves data without modifying state.
Register the Cwiki MCP server in PolicyLayer and add a rule for cwiki_get_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 CwikiMCP. Nothing to install.
cwiki_get_page 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 cwiki_get_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 cwiki_get_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.
cwiki_get_page is provided by the Cwiki MCP server (justinmclean/cwikimcp). 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 →