MCP-Server
A Flask-based MCP server with web GUI that provides utility tools for mathematical calculations, text analysis, string transformations, timestamps, and Fibonacci sequence generation.
README
MCP-Server
Simple MCP (Model Context Protocol) server with a Flask-based web GUI
Overview
This is a simple MCP server implementation that exposes various tools through a web-based GUI. The server includes several example tools that demonstrate different functionalities:
- calculate: Perform basic mathematical operations (add, subtract, multiply, divide)
- text_analyzer: Analyze text and provide statistics (word count, character count, etc.)
- timestamp: Get current timestamp in various formats
- string_transform: Transform strings (uppercase, lowercase, reverse, title case)
- fibonacci: Generate Fibonacci sequence
Installation
- Clone this repository:
git clone https://github.com/thedcfix/MCP-Server.git
cd MCP-Server
- Install dependencies:
pip install -r requirements.txt
Usage
- Start the Flask server:
python app.py
- Open your web browser and navigate to:
http://localhost:5000
- The GUI will display:
- Server information and statistics
- List of all available tools with their descriptions and parameters
- A test section where you can execute tools with custom parameters
API Endpoints
The server exposes the following REST API endpoints:
GET /- Web GUI interfaceGET /api/tools- List all available toolsGET /api/server-info- Get server informationPOST /api/execute- Execute a tool with parameters
Example API Usage
# List all tools
curl http://localhost:5000/api/tools
# Execute the calculate tool
curl -X POST http://localhost:5000/api/execute \
-H "Content-Type: application/json" \
-d '{"tool_name": "calculate", "parameters": {"operation": "add", "a": 10, "b": 5}}'
# Analyze text
curl -X POST http://localhost:5000/api/execute \
-H "Content-Type: application/json" \
-d '{"tool_name": "text_analyzer", "parameters": {"text": "Hello world!"}}'
Project Structure
MCP-Server/
├── app.py # Flask web application
├── mcp_server.py # MCP server implementation with tools
├── templates/
│ └── index.html # Web GUI template
├── requirements.txt # Python dependencies
└── README.md # This file
Adding New Tools
To add a new tool to the MCP server:
- Open
mcp_server.py - Add a new method to handle the tool (e.g.,
_my_tool) - Register the tool in the
_register_tools()method with its metadata - The tool will automatically appear in the web GUI
License
MIT License
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。