Python FastMCP Server
A Python-based MCP server demonstrating basic math and text tools, supporting both SSE and STDIO transports for integration with AI assistants like Cline in VS Code.
README
Python FastMCP Server
This is a Python-based Model Context Protocol (MCP) server built using the FastMCP framework. It demonstrates how to create, modularize, and interact with an MCP server using both Server-Sent Events (SSE) and STDIO transport mechanisms.
Project Structure
server.py: The main entry point for the MCP server. It initializes theFastMCPinstance and registers tools from thetoolspackage.client.py: An automated Python client that connects to the server and tests the available tools. It connects using the STDIO transport by default and runs the server as a background subprocess.tools/: A package containing the modularized MCP tools.math_tools.py: Contains mathematical tools likecalculate_sumandfilter_even_numbers.text_tools.py: Contains text processing tools likeanalyze_text.
requirements.txt: Python dependencies required for this project.
Setup
- Ensure you have Python installed.
- Create and activate a virtual environment (recommended):
python -m venv venv venv\Scripts\activate # On Windows # source venv/bin/activate # On macOS/Linux - Install the dependencies:
pip install -r requirements.txt
Running the Project
Running the Client (STDIO Mode)
The simplest way to test the project is to run the client. In STDIO mode, the client will automatically start server.py in the background, discover the available tools, and execute a sample tool call (calculate_sum).
python client.py
Running the Server (SSE Mode)
If you wish to communicate over a network, you can run the server in Server-Sent Events (SSE) mode:
- Start the server in a terminal:
python server.py sse - Open a second terminal and run the client in SSE mode:
python client.py sse
VS Code Integration
This server is fully compatible with Cline VS Code. To use it, you can add it to your config.json:
{
"mcpServers": {
"my-python-server": {
"command": "path\\to\\your\\venv\\Scripts\\python.exe",
"args": [
"path\\to\\your\\server.py"
]
}
}
}
(Make sure to use absolute paths to your python executable and server.py file).
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。