AI agents call get_languages 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 queries and retrieves available language translations for a given page, returning informational metadata about available content. It performs no data modification, deletion, or execution of code. The blast radius of misuse is minimal—an agent could only retrieve language availability information across Wikimedia projects.
From the tool's definition Tool 'get_languages' retrieves language versions of a Wikimedia page. The verb 'Get' and the description 'Get versions' indicate a read-only retrieval operation with no side effects.
Attacks that exploit this kind of access
Get versions of a Wikimedia page in other languages. Parameters: title (required), project (e.g.,. 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_languages: 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_languages 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_languages 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_languages. 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_languages 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 →