
MCP Wikipedia Server
A production-ready server that provides Wikipedia search and content retrieval tools through the Model Context Protocol, enabling AI assistants to search for articles, list sections, and retrieve specific content.
README
MCP Wikipedia Server
A production-ready Model Context Protocol (MCP) server that provides Wikipedia search and content retrieval tools using FastMCP and Python 3.11.
🚀 Quick Start
# 1. Set up environment (one-time setup)
./setup.sh
# 2. Start the server
source .venv311/bin/activate
cd src/mcp_server && python mcp_server.py
# 3. Test with example client
python example_client.py
🎯 Features
- Wikipedia Search: Find articles with intelligent search and get comprehensive summaries
- Section Listing: Extract all section titles from any Wikipedia article
- Content Retrieval: Get specific section content with proper formatting
- MCP Protocol: Full Model Context Protocol compatibility for AI assistant integration
- FastMCP Framework: Built on the efficient FastMCP library for optimal performance
- Python 3.11: Modern Python with latest features and performance improvements
📚 Documentation
Document | Description |
---|---|
📖 Complete Guide | Detailed setup, usage, and development instructions |
⚡ Quick Reference | Common commands and tool summaries |
🔧 Setup Script | Automated environment setup and verification |
💡 Example Client | Sample usage and integration examples |
🛠️ Available Tools
Tool | Purpose | Example Usage |
---|---|---|
fetch_wikipedia_info |
Search Wikipedia and get article summaries | Search for "Python programming" |
list_wikipedia_sections |
Get all section titles from an article | List sections of "Machine Learning" |
get_section_content |
Retrieve specific section content | Get "History" section from "Artificial Intelligence" |
🏗️ Project Structure
MCPClientServer/
├── 📁 src/mcp_server/ # Core server implementation
│ ├── mcp_server.py # Main MCP Wikipedia server
│ └── mcp_client.py # Example MCP client
├── 📁 tests/ # Comprehensive test suite
│ ├── test_server.py # Unit tests (pytest)
│ ├── test_integration.py # Integration tests
│ ├── test_performance.py # Performance benchmarks
│ ├── test_mcp_compliance.py # MCP protocol compliance
│ ├── quick_test.py # Fast validation script
│ ├── run_tests.py # Unified test runner
│ └── README.md # Testing documentation
├── 📁 .venv311/ # Python 3.11 virtual environment
├── 🔧 setup.sh # Automated setup script
├── 💡 example_client.py # Usage examples and demos
├── 📖 GUIDE.md # Complete documentation
├── ⚡ QUICK_REF.md # Quick reference
├── 📄 pytest.ini # Test configuration
├── 📄 requirements-test.txt # Test dependencies
└── 📄 pyproject.toml # Project configuration
🚦 Prerequisites
- macOS (tested on Apple Silicon and Intel)
- Python 3.11+ (installed via pyenv recommended)
- Git (for version control)
📦 Installation Options
Option 1: Automated Setup (Recommended)
chmod +x setup.sh
./setup.sh
Option 2: Manual Setup
# Set up Python 3.11 environment
pyenv install 3.11.10
pyenv local 3.11.10
# Create and activate virtual environment
python -m venv .venv311
source .venv311/bin/activate
# Install dependencies
pip install --upgrade pip
pip install wikipedia mcp fastmcp
🔌 Integration Examples
With Claude Desktop (MCP Client)
{
"mcpServers": {
"wikipedia": {
"command": "python",
"args": ["/path/to/MCPClientServer/src/mcp_server/mcp_server.py"],
"env": {
"PYTHONPATH": "/path/to/MCPClientServer/.venv311/lib/python3.11/site-packages"
}
}
}
}
Direct Python Usage
from mcp_client import WikipediaClient
client = WikipediaClient()
result = await client.search_wikipedia("Artificial Intelligence")
print(result)
🧪 Testing
Quick Testing
# Fast validation (10 seconds)
python tests/quick_test.py
# Comprehensive test suite (5 minutes)
python tests/run_tests.py
Advanced Testing
# Install test dependencies
pip install -r requirements-test.txt
# Run specific test suites
python tests/run_tests.py --unit # Unit tests only
python tests/run_tests.py --integration # Integration tests only
python tests/run_tests.py --performance # Performance benchmarks
python tests/run_tests.py --mcp # MCP compliance tests
# Using pytest directly
python -m pytest tests/test_server.py -v --cov=src
Test Suite Overview
- Unit Tests: Individual function and component testing
- Integration Tests: End-to-end workflow validation
- Performance Tests: Response time and load benchmarks
- MCP Compliance: Protocol specification validation
- 95%+ Code Coverage: Comprehensive test coverage
See tests/README.md for complete testing documentation.
🐛 Troubleshooting
Issue | Solution |
---|---|
ModuleNotFoundError: No module named 'mcp' |
Run pip install mcp fastmcp in activated environment |
Python version issues |
Ensure Python 3.11+ with python --version |
Server won't start |
Check if port is available, verify dependencies |
Wikipedia API errors |
Check internet connection, try different search terms |
For detailed troubleshooting, see GUIDE.md.
🤝 Contributing
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature
) - Commit your changes (
git commit -m 'Add amazing feature'
) - Push to the branch (
git push origin feature/amazing-feature
) - Open a Pull Request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🔗 Resources
- Model Context Protocol Documentation
- FastMCP Framework
- Wikipedia API Documentation
- Python 3.11 Features
🌟 Support
If you find this project helpful, please consider giving it a star ⭐ on GitHub!
Made with ❤️ for the MCP community
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。
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。
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。

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。
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。
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。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。