AI agents use wiki_set_lang to create or update resources in Basic MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Basic MCP environment.
This tool modifies state by changing a Wikipedia language setting, which is a write operation. The severity is low because: (1) the change is reversible (language can be changed back), (2) it only affects the tool's own configuration, not shared data or external systems, and (3) there is minimal blast radius if misused—an agent changing the language would only affect subsequent Wikipedia queries, with no cascading…
From the tool's definition Tool is named 'wiki_set_lang' and described as 'Set Wikipedia language'. The verb 'Set' indicates a modification operation.
Attacks that exploit this kind of access
Set Wikipedia language. It is categorised as a Write tool in the Basic MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Basic MCP server in PolicyLayer and add a rule for wiki_set_lang: 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 Basic MCP. Nothing to install.
wiki_set_lang is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the wiki_set_lang 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_set_lang. 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_set_lang is provided by the Basic MCP server (nimishgautam/basic-mcp). 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 →