MCP Time Server

MCP Time Server

A TypeScript server that provides time-related tools through the Model Context Protocol, allowing users to get current time in various timezones and convert times between different IANA timezones.

Category
访问服务器

README

MCP Time Server (mcp-time-srv)

A simple Model Context Protocol (MCP) server implemented in TypeScript that provides tools for time-related queries, including getting the current time in various timezones and converting times between timezones.

This server supports both modern Streamable HTTP and legacy HTTP+SSE MCP transport protocols.

Features

Provides the following MCP tools:

  • get_current_time: Returns the current time in a specified IANA timezone.
  • convert_time: Converts a given time from a source IANA timezone to a target IANA timezone.

Prerequisites

  • Node.js (v18 or later recommended)
  • npm (usually comes with Node.js)
  • Docker (Optional, for running in a container)

Setup

  1. Clone the repository (if you haven't already):

    # git clone <your-repo-url>
    # cd mcp-time-srv
    
  2. Install dependencies:

    npm install
    

Running Locally

  1. Build the TypeScript code:

    npm run build
    

    This compiles the TypeScript source in src/ to JavaScript in dist/.

  2. Run the server: You can run the server using ts-node (for development) or directly with node after building.

    • Using ts-node:
      npx ts-node src/server.ts
      
    • Using node (after building):
      node dist/server.js
      

The server will start, typically listening on port 3000.

MCP Time server listening on http://localhost:3000

Running with Docker (Optional)

A Dockerfile is provided for building and running the server in a container.

  1. Build the Docker image:

    docker build -t mcp-time-srv .
    
  2. Run the container:

    docker run -d -p 3000:3000 --name my-mcp-server mcp-time-srv
    
    • -d: Run in detached mode (in the background).
    • -p 3000:3000: Map port 3000 on your host to port 3000 in the container.
    • --name my-mcp-server: Assign a name to the container for easier management.

The server will be running inside the container, accessible at http://localhost:3000.

To stop the container:

docker stop my-mcp-server

To view logs:

docker logs my-mcp-server

Testing with the Client

A simple test client script (src/client.ts) is included to demonstrate interacting with the server's tools.

  1. Ensure the server is running (either locally or in Docker).
  2. Run the client:
    npx ts-node src/client.ts
    

The client will connect to the server (using SSE transport by default), list the available tools, call each tool with example arguments (including some designed to test error handling), and print the results.

Tool Details

get_current_time

Returns the current time in the specified timezone.

  • Input Argument:
    • timezone (string, optional): An IANA timezone name (e.g., America/New_York, Europe/London). If omitted, defaults to the server's local timezone.
  • Output: A JSON object containing:
    • timezone (string): The effective timezone used.
    • datetime (string): The current time in ISO 8601 format with offset (e.g., 2025-04-26T01:39:15Z).

convert_time

Converts a time from a source timezone to a target timezone.

  • Input Arguments:
    • source_timezone (string, optional): Source IANA timezone name. Defaults to server's local timezone if omitted.
    • time (string, required): The time to convert in 24-hour HH:MM format (e.g., 14:30).
    • target_timezone (string, optional): Target IANA timezone name. Defaults to server's local timezone if omitted.
  • Output: A JSON object containing:
    • source (object): Details of the time in the source timezone (timezone, datetime).
    • target (object): Details of the converted time in the target timezone (timezone, datetime).
    • time_difference (string): The difference between the target and source timezone offsets (e.g., +8h, -5h, +5.75h).

License

This project is licensed under the MIT License - see the LICENSE file for details.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选