The Wikipedia MCP Server provides real-time access to Wikipedia data via the Model Context Protocol (MCP), enabling LLMs to ground their responses in factual, up-to-date information. It exposes a suite of MCP tools that let clients search for articles, fetch full article content, obtain concise summaries, extract specific sections, discover internal links, and identify related topics. Additional capabilities include locating article coordinates, generating query-focused summaries, summarizing specific sections, and extracting key facts. The server supports multi-language usage and country/locale mappings, allowing users to specify language codes (via --language) or country codes (via --country), with automatic mapping to appropriate Wikipedia language editions. Language variants (e.g., zh-hans, zh-tw, sr-latn, sr-cyrl, ku-*) are also supported. Optional caching can be enabled to improve performance, and a Personal Access Token can be used to mitigate rate limits. The system is transportable via stdio or SSE, is compatible with Google ADK-compatible tooling, and is designed to work behind authenticating proxies or private networks for secure deployments.