AI agents call get_featured to retrieve information from Wikimedia without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only retrieval of pre-curated content from Wikimedia projects. It has no side effects, cannot modify or delete data, and poses minimal risk if misused by an AI agent. The worst-case scenario is retrieving unwanted information, which is a low-severity risk.
From the tool's definition The tool retrieves featured Wikimedia content (featured article, most read pages, picture of the day) for a specified date. The description uses retrieval language: 'Get', 'Returns'. No modification, deletion, or execution capabilities are indicated.
Attacks that exploit this kind of access
Get featured Wikimedia content for a date. Returns featured article, most read pages, and picture of the day. Parameters: date (YYYY/MM/DD, default today), project (. It is categorised as a Read tool in the Wikimedia MCP Server, which means it retrieves data without modifying state.
Register the Wikimedia MCP server in PolicyLayer and add a rule for get_featured: 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 Wikimedia. Nothing to install.
get_featured 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_featured 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_featured. 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_featured is provided by the Wikimedia MCP server (rapidmcp/wikimedia). 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 →