wikipedia-mcp MCP — 使用場景, 安裝 & 即時演示

為什麼要用

核心特性

10+ tools: search, article, summary, sections, links, coordinates, related topics
Multi-language with regional variants (zh-Hant, zh-Hans, sr-Latn, etc.)
Optional caching for repeat queries
Country/locale codes accepted alongside language codes
stdio, HTTP, streamable-HTTP transports

即時演示

實際使用效果

wikipedia.replay ▶ 就緒

0/0

安裝

選擇你的客戶端

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "wikipedia": {
      "command": "uvx",
      "args": [
        "wikipedia-mcp"
      ],
      "_inferred": true
    }
  }
}

開啟 Claude Desktop → Settings → Developer → Edit Config。儲存後重啟應用。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "wikipedia": {
      "command": "uvx",
      "args": [
        "wikipedia-mcp"
      ],
      "_inferred": true
    }
  }
}

Cursor 使用與 Claude Desktop 相同的 mcpServers 格式。專案級設定優先於全域。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "wikipedia": {
      "command": "uvx",
      "args": [
        "wikipedia-mcp"
      ],
      "_inferred": true
    }
  }
}

點擊 Cline 側欄中的 MCP Servers 圖示，然後選 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "wikipedia": {
      "command": "uvx",
      "args": [
        "wikipedia-mcp"
      ],
      "_inferred": true
    }
  }
}

格式與 Claude Desktop 相同。重啟 Windsurf 生效。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "wikipedia",
      "command": "uvx",
      "args": [
        "wikipedia-mcp"
      ]
    }
  ]
}

Continue 使用伺服器物件陣列，而非映射。

~/.config/zed/settings.json

{
  "context_servers": {
    "wikipedia": {
      "command": {
        "path": "uvx",
        "args": [
          "wikipedia-mcp"
        ]
      }
    }
  }
}

加入 context_servers。Zed 儲存後熱重載。

claude mcp add wikipedia -- uvx wikipedia-mcp

一行命令搞定。用 claude mcp list 驗證，claude mcp remove 移除。

使用場景

實戰用法： wikipedia-mcp

Cite Wikipedia instead of relying on model memory

👤 Anyone doing research-style Q&A ⏱ ~2 min beginner

何時使用： The model's training cutoff is older than the facts you need (new events, refreshed biographies, updated stats).

步驟

Ask with citation requirement

When did the 2026 Winter Olympics happen and where? Use the wikipedia MCP and cite the article.✓ 已複製

→ Answer + Wikipedia article title/URL

結果： Answers with a verifiable source, less hallucination.

注意事項

Wikipedia itself has errors / vandalism — For high-stakes facts, cross-check with a second source

Build a one-page dossier on a person or topic

👤 Journalists, prep-for-meeting folks ⏱ ~10 min beginner

何時使用： You're meeting someone unfamiliar or writing about a new-to-you topic and want structured context fast.

步驟

Summary first

Get a summary of [person/topic] from Wikipedia. Then list sections so I can pick which to deep-read.✓ 已複製

→ Summary + TOC
Pull the key sections

Give me full text of the 'Career' and 'Controversies' sections.✓ 已複製

→ Section text
Related threads

What related Wikipedia topics should I also skim?✓ 已複製

→ Related topic list with 1-line summaries

結果： 10-minute dossier better than ad-hoc googling.

注意事項

Wikipedia page doesn't exist for the person — Fall back to web search (firecrawl) for less-covered subjects

搭配使用： notion

Compare how a topic is covered across languages

👤 Researchers, translators, international ops ⏱ ~15 min intermediate

何時使用： You suspect the English and Chinese Wikipedia articles on a topic differ materially (they often do for geopolitical topics).

步驟

Pull both versions

Get Wikipedia articles on [topic] in English and Simplified Chinese (zh-Hans).✓ 已複製

→ Two article bodies
Diff the framing

What facts are in one but not the other? How does each frame the controversy?✓ 已複製

→ Structured comparison

結果： Nuanced multi-perspective understanding.

注意事項

Translation quality varies — Ask Claude to quote original language too for contested phrasings

組合

與其他 MCP 搭配，撬動十倍槓桿

wikipedia + notion

Build a 'places visited' Notion DB with Wikipedia summaries

For each row in my 'Trips' Notion DB, fetch the Wikipedia summary of the destination city and populate the 'About' column.✓ 已複製

wikipedia + google-map

Show a topic on a map

Get coordinates of these 10 battles from Wikipedia; render them on a static Google map.✓ 已複製

工具

此 MCP 暴露的能力

工具	輸入參數	何時呼叫	成本
search_wikipedia	query: str, language?: str, limit?: int	Find candidate articles	free
get_article	title: str, language?: str	Need full content; use summary if 2-3 sentences suffice	free
get_summary	title, language?	Quick context without full article cost	free
get_sections	title, language?	Decide which sections to pull before pulling full article	free
get_section	title, section, language?	Cheaper than full article when you know what you want	free
get_links	title, language?	Discover related articles	free
get_coordinates	title	Plot an article's place on a map	free
get_related_topics	title	Research-mode expansion	free

成本與限制

運行它的成本

API 配額: Wikipedia rate limits: ~200 requests/sec from an IP; add delays for long scripts
每次呼叫 Token 數: Full articles 2k-15k tokens; summaries 200-500
費用: Free
提示: Always start with get_summary or get_sections — avoid pulling a whole get_article unless you need the full text.

安全

權限、密鑰、影響範圍

憑證儲存： Optional Wikimedia OAuth token for higher rate limits

資料出站： Outbound to Wikipedia's servers only

Wikipedia is crowd-edited — always treat as a starting point, not final source for contested facts.
Anonymous requests are throttled more aggressively; authenticate if you hit limits.

故障排查

常見錯誤與修復

403 Forbidden on heavy use

Anonymous rate limit hit. Provide a personal access token or slow down (add sleep).

Page not found

Titles are case-sensitive and disambiguation-specific. Use search_wikipedia first to get the canonical title.

Chinese article returns Traditional when I want Simplified

Pass language=zh-Hans or language=zh-Hant explicitly.

替代方案

wikipedia-mcp 對比其他方案

替代方案	何時用它替代	權衡
DBpedia / Wikidata MCP	You want structured data (infobox fields) rather than prose	Better for querying facts; worse for reading
Direct Wikipedia API via fetch MCP	You need maximum control	You parse the JSON yourself

wikipedia-mcp

為什麼要用

核心特性

即時演示

實際使用效果

安裝

選擇你的客戶端

使用場景

實戰用法： wikipedia-mcp

Cite Wikipedia instead of relying on model memory

步驟

注意事項

Build a one-page dossier on a person or topic

步驟

注意事項

Compare how a topic is covered across languages

步驟

注意事項

組合

與其他 MCP 搭配，撬動十倍槓桿

工具

此 MCP 暴露的能力

成本與限制

運行它的成本

安全

權限、密鑰、影響範圍

故障排查

常見錯誤與修復

替代方案

wikipedia-mcp 對比其他方案

更多

資源