Nhập term, baseLang (mặc định
AI agents call wiki_multi to retrieve information from Mcp Web Calc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information from Wikipedia based on input terms and language parameters. Wikipedia queries are read-only operations that retrieve data without modifying it, creating side effects, or executing arbitrary operations. While the description is incomplete, the naming convention and server context strongly suggest this is a safe information retrieval tool.
From the tool's definition Tool name 'wiki_multi' is part of a Wikipedia tools family on a server described as providing 'Wikipedia tools'.
Attacks that exploit this kind of access
Nhập term, baseLang (mặc định. It is categorised as a Read tool in the Mcp Web Calc MCP Server, which means it retrieves data without modifying state.
Register the Mcp Web Calc MCP server in PolicyLayer and add a rule for wiki_multi: 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 Mcp Web Calc. Nothing to install.
wiki_multi 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_multi 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_multi. 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_multi is provided by the Mcp Web Calc MCP server (khanhs-234/mcp-web-calc). 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 →