AI agents call wiki.search 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 full-text search across wiki content and returns matching snippets—a classic read operation with no side effects. It does not create, modify, delete, or execute operations. The blast radius of misuse is minimal; an attacker could only retrieve existing information already accessible to authorized users.
From the tool's definition Tool description states 'Search the wiki for pages matching a query. Returns snippets with citations for verification.' The name 'search' and the mechanism of querying and returning results with no modification capability indicate a read-only retrieval…
Attacks that exploit this kind of access
Search the wiki for pages matching a query. Returns snippets with citations for verification. 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 wiki.search: 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.
wiki.search 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 wiki.search 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.search. 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.search is provided by the Wiki MCP server (raydestar/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 →