FastMCP Multi-Tool Server
Provides comprehensive utility tools including file operations, weather information, system monitoring, mathematical calculations, text search, and safe command execution. Enables users to perform various system and data operations through a unified MCP interface with built-in security features.
README
FastMCP Multi-Tool Server
A comprehensive Model Context Protocol (MCP) server built with FastMCP that provides various utility tools.
Features
This MCP server includes the following tools:
🕒 Time & Date
- get_current_time: Get the current date and time
🌤️ Weather
- get_weather: Get weather information for any city (requires OpenWeatherMap API key)
📁 File Operations
- create_file: Create new files with specified content
- read_file: Read content from existing files
- list_directory: List contents of directories
- create_temporary_file: Create temporary files
🔍 Search & Analysis
- search_files: Search for text patterns in files within a directory
- calculate_expression: Safely evaluate mathematical expressions
💻 System Operations
- execute_command: Execute shell commands safely (with security restrictions)
- get_system_info: Get detailed system information (CPU, memory, disk usage)
Installation
Quick Setup
Windows:
scripts\build.bat
Linux/macOS:
chmod +x scripts/build.sh && scripts/build.sh
Cross-platform (Python):
python scripts/build.py
Manual Installation
- Install Python dependencies:
pip install -r requirements.txt
- (Optional) Configure environment variables:
# Copy the example environment file
cp .env.example .env
# Edit .env and add your OpenWeatherMap API key if needed
Usage
Running the Server
To run the MCP server:
python server.py
The server will start and listen for MCP connections.
Configuration with Claude Desktop
To use this server with Claude Desktop, add the following configuration to your claude_desktop_config.json:
{
"mcpServers": {
"multi-tool-server": {
"command": "python",
"args": ["C:/github/mcp-py/server.py"],
"cwd": "C:/github/mcp-py"
}
}
}
Note: Update the paths to match your actual installation directory.
Configuration File Location
The Claude Desktop configuration file is typically located at:
- Windows:
%APPDATA%/Claude/claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Tool Examples
File Operations
# Create a new file
create_file("./example.txt", "Hello, World!")
# Read a file
read_file("./example.txt")
# List directory contents
list_directory("./")
Weather Information
# Get weather for a city (requires API key)
get_weather("London")
Mathematical Calculations
# Calculate mathematical expressions
calculate_expression("2 + 2 * 3")
calculate_expression("sqrt(16) + pow(2, 3)")
File Search
# Search for text in Python files
search_files("./", "import", ".py")
System Information
# Get system details
get_system_info()
Command Execution
# Execute safe commands
execute_command("echo Hello World")
execute_command("ls -la", "/tmp") # Unix
execute_command("dir", "C:\\") # Windows
Security Features
- Command Filtering: Dangerous commands are blocked automatically
- Safe Expression Evaluation: Mathematical expressions are evaluated in a secure environment
- Timeout Protection: Commands have a 30-second timeout limit
- Path Validation: File operations validate paths to prevent unauthorized access
Environment Variables
OPENWEATHER_API_KEY: Your OpenWeatherMap API key for weather functionalityMCP_SERVER_NAME: Custom server name (optional)MCP_SERVER_VERSION: Server version (optional)
Dependencies
fastmcp: FastMCP framework for MCP server developmentrequests: HTTP library for API callspython-dotenv: Environment variable managementpydantic: Data validation and settings managementpsutil: System and process utilities
Troubleshooting
Common Issues
-
Import Errors: Make sure all dependencies are installed:
pip install -r requirements.txt -
Weather Tool Not Working: Ensure you have a valid OpenWeatherMap API key set in the
.envfile. -
Permission Errors: Make sure the server has appropriate file system permissions for the operations you're trying to perform.
-
Command Execution Fails: Some commands may be blocked for security reasons. Check the error message for details.
Development
To extend this server with additional tools:
- Add new tool functions using the
@mcp.tool()decorator - Follow the existing pattern for error handling and return formats
- Update this README with documentation for new tools
License
This project is open source. Feel free to modify and distribute according to your needs.
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。