Wikipedia MCP Server
Provides comprehensive access to Wikipedia content including article search, full text retrieval, summaries, categories, links, images, language versions, and external references through 9 specialized tools.
README
wiki-mcp
MCP (Model Context Protocol) server for Wikipedia. Provides tools to search articles, retrieve content, summaries, categories, links, images, language versions, and external references.
Features
- 9 Wikipedia tools for comprehensive article access
- Proper TypeScript types for all API responses
- Request timeout handling
- Error handling with informative messages
- Modular architecture
Tools
| Tool | Description |
|---|---|
wiki_search |
Search Wikipedia for articles matching a query |
wiki_get_article |
Get the full text content of an article |
wiki_get_summary |
Get a short summary of an article |
wiki_random |
Get random Wikipedia articles |
wiki_get_categories |
Get categories an article belongs to |
wiki_get_links |
Get internal Wikipedia links from an article |
wiki_get_images |
Get images used in an article |
wiki_get_languages |
Get available language versions of an article |
wiki_get_references |
Get external references/links from an article |
Installation
Quick install (recommended)
bunx wiki-mcp install
This automatically adds wiki-mcp to Claude Desktop and Claude Code.
Manual install
# Or install globally
bun add -g wiki-mcp
npm install -g wiki-mcp
Via Smithery
npx @smithery/cli install wiki-mcp
From source
git clone https://github.com/msilverblatt/wiki-mcp.git
cd wiki-mcp
bun install
Usage
With Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"wikipedia": {
"command": "bunx",
"args": ["wiki-mcp"]
}
}
}
With Claude Code
Add to your Claude Code MCP settings (~/.claude/settings.json):
{
"mcpServers": {
"wikipedia": {
"command": "bunx",
"args": ["wiki-mcp"]
}
}
}
Standalone
bun run index.ts
The server communicates via stdio using the MCP protocol.
Tool Examples
wiki_search
Search for articles:
{
"query": "artificial intelligence",
"limit": 5
}
Returns:
[
{
"title": "Artificial intelligence",
"snippet": "Artificial intelligence (AI) is the intelligence of machines...",
"pageid": 1234
}
]
wiki_get_article
Get full article content:
{
"title": "JavaScript"
}
Returns plain text article content.
wiki_get_summary
Get article summary:
{
"title": "TypeScript"
}
Returns:
{
"title": "TypeScript",
"description": "Programming language",
"extract": "TypeScript is a strongly typed programming language...",
"url": "https://en.wikipedia.org/wiki/TypeScript"
}
wiki_get_categories
Get article categories:
{
"title": "Python (programming language)",
"limit": 10
}
Returns:
{
"title": "Python (programming language)",
"categories": ["Programming languages", "Scripting languages", "..."]
}
wiki_get_links
Get internal links:
{
"title": "Machine learning",
"limit": 50
}
Returns:
{
"title": "Machine learning",
"links": ["Artificial intelligence", "Data science", "..."]
}
wiki_get_images
Get article images:
{
"title": "Solar System",
"limit": 20
}
Returns:
{
"title": "Solar System",
"images": [
{
"title": "Solar System.jpg",
"url": "https://en.wikipedia.org/wiki/File:Solar_System.jpg"
}
]
}
wiki_get_languages
Get available translations:
{
"title": "Albert Einstein"
}
Returns:
{
"title": "Albert Einstein",
"languageCount": 200,
"languages": [
{
"language": "Deutsch",
"code": "de",
"title": "Albert Einstein",
"url": "https://de.wikipedia.org/wiki/Albert_Einstein"
}
]
}
wiki_get_references
Get external references:
{
"title": "Climate change",
"limit": 30
}
Returns:
{
"title": "Climate change",
"references": ["https://www.ipcc.ch/", "..."]
}
wiki_random
Get random articles:
{
"count": 3
}
Returns:
[
{ "title": "Random Article 1", "id": 12345 },
{ "title": "Random Article 2", "id": 67890 }
]
Development
# Run tests
bun test
# Type check
bun run typecheck
# Start server
bun run start
Project Structure
wiki-mcp/
├── index.ts # Entry point
├── src/
│ ├── api.ts # Wikipedia API client
│ ├── server.ts # MCP server setup
│ ├── types.ts # TypeScript interfaces
│ └── tools/
│ ├── index.ts # Tool registration
│ ├── search.ts # wiki_search
│ ├── article.ts # wiki_get_article
│ ├── summary.ts # wiki_get_summary
│ ├── random.ts # wiki_random
│ ├── categories.ts # wiki_get_categories
│ ├── links.ts # wiki_get_links
│ ├── images.ts # wiki_get_images
│ ├── languages.ts # wiki_get_languages
│ └── references.ts # wiki_get_references
└── tests/
├── api.test.ts # API helper tests
└── tools.test.ts # Tool integration tests
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。