MCP Deployment
A simple demonstration MCP server that provides a sum_numbers tool for calculating the sum of a list of integers, built using the FastMCP framework.
README
MCP Deployment
A Model Context Protocol (MCP) server that exposes a sum_numbers tool for summing lists of integers. This project demonstrates a simple MCP server implementation using FastMCP.
Project Overview
This MCP deployment project provides:
- sum_numbers Tool: A simple tool that takes a list of integers and returns their sum
- FastMCP Server: Built on the MCP FastMCP framework for easy server implementation
- Python 3.13+: Uses modern Python with type hints and async support
Installation
Prerequisites
- Python 3.13 or higher
uvpackage manager (recommended) orpip
Using uv (Recommended)
-
Install
uv(if not already installed):# On Windows powershell -c "irm https://astral.sh/uv/install.ps1 | iex" # On macOS/Linux curl -LsSf https://astral.sh/uv/install.sh | sh -
Clone the repository:
git clone https://github.com/Mandapati-SuryanarayanaRaju/mcp-deployment.git cd mcp-deployment -
Create a virtual environment and install dependencies:
uv sync -
Run the MCP server:
uv run mcp-server
Using pip
-
Clone the repository:
git clone https://github.com/Mandapati-SuryanarayanaRaju/mcp-deployment.git cd mcp-deployment -
Create a virtual environment:
python -m venv .venv source .venv/bin/activate # On Windows: .venv\Scripts\activate -
Install dependencies:
pip install -e . -
Run the MCP server:
mcp-server
Configuration
Claude Desktop Configuration
To use this MCP server with Claude Desktop, add the following configuration to your claude_desktop_config.json:
{
"mcpServers": {
"Sum-numbers": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/Mandapati-SuryanarayanaRaju/mcp-deployment@main",
"mcp-server"
]
}
}
}
Location of claude_desktop_config.json:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Alternative Local Configuration
If you prefer to run the server locally, use:
{
"mcpServers": {
"sum-numbers": {
"command": "python",
"args": [
"-m",
"mcpserver"
],
"cwd": "/path/to/mcp-deployment"
}
}
}
Available Tools
sum_numbers
Sums a list of integers.
Parameters:
numbers(list[int]): A list of integers to be summed
Returns:
- (int): The sum of all integers in the list
Example:
result = sum_numbers([1, 2, 3, 4, 5])
# Returns: 15
Project Structure
mcp-deployment/
src/
mcpserver/
__init__.py
__main__.py
deployment.py
pyproject.toml
README.md
uv.lock
Dependencies
mcp[cli]>=1.23.1: Model Context Protocol library with CLI support- Python 3.13+
Development
To contribute or modify the server:
-
Install in development mode:
uv sync -
Edit
src/mcpserver/deployment.pyto add new tools or modify existing ones -
Test locally:
uv run mcp-server
License
This project is open source. See LICENSE file for details.
Support
For issues or questions, please open an issue on GitHub: mcp-deployment Issues
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。