Simple MCP Server
A lightweight Model Context Protocol server that provides an in-memory key-value store with get, set, delete, list, and clear operations for MCP-compatible AI assistants and clients.
README
Simple MCP Server
A simple Model Context Protocol (MCP) server that provides value lookup operations. This server implements a basic key-value store that can be accessed by MCP-compatible AI assistants and clients.
Features
- In-memory key-value store: Store and retrieve data during the session
- JSON support: Automatically parses and formats JSON values
- Multiple operations: Get, set, delete, list, and clear operations
- MCP protocol compliance: Uses the standard MCP protocol for communication
- Easy integration: Can be used with any MCP-compatible client
Available Tools
The server provides the following tools that can be called by MCP clients:
get_value
Retrieve a value from the store by key.
- Parameters:
key(string) - The key to look up - Returns: The value associated with the key, or an error message if not found
set_value
Store a key-value pair in the store.
- Parameters:
key(string) - The key to storevalue(string) - The value to store (automatically parsed as JSON if valid)
- Returns: Confirmation message
delete_value
Remove a key-value pair from the store.
- Parameters:
key(string) - The key to delete - Returns: Confirmation message
list_keys
List all keys currently in the store.
- Parameters: None
- Returns: A formatted list of all keys
clear_values
Clear all key-value pairs from the store.
- Parameters: None
- Returns: Confirmation message
get_store_info
Get information about the current state of the store.
- Parameters: None
- Returns: Store statistics and sample keys
Installation
- Clone this repository:
git clone https://github.com/jmgress/simple-mcp.git
cd simple-mcp
- Install dependencies:
pip install -e .
Usage
Running the Server
Start the MCP server using stdio transport:
simple-mcp-server
Or run directly with Python:
python -m simple_mcp.server
Testing the Server
You can test the server functionality using the included test script:
python test_server.py
This will demonstrate all available operations and show you how the server responds.
Using with MCP Clients
The server can be used with any MCP-compatible client. Configure your client to connect to this server using stdio transport.
Example client configuration (varies by client):
{
"servers": {
"simple-mcp": {
"command": "simple-mcp-server",
"transport": "stdio"
}
}
}
Example Operations
Here are some example operations you can perform:
# Store a simple string value
set_value(key="greeting", value="Hello, World!")
# Store JSON data
set_value(key="user", value='{"name": "Alice", "age": 30}')
# Retrieve values
get_value(key="greeting") # Returns: "Hello, World!"
get_value(key="user") # Returns formatted JSON
# List all keys
list_keys() # Returns: "Keys in store (2 total): greeting, user"
# Get store information
get_store_info() # Returns current store statistics
# Clean up
delete_value(key="greeting")
clear_values() # Removes all data
Architecture
The server is built using:
- FastMCP: A high-level MCP server framework
- JSON-RPC 2.0: For client-server communication
- Pydantic: For data validation and serialization
- asyncio: For asynchronous operation
The value store is currently in-memory only, meaning data is lost when the server restarts. This makes it suitable for temporary storage and demonstration purposes.
Development
To set up for development:
# Install in development mode with dev dependencies
pip install -e ".[dev]"
# Run tests
python test_server.py
# Format code
black src/
# Lint code
ruff check src/
License
This project is licensed under the MIT License - see the LICENSE file for details.
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。