MCP Wait Server

by Amico1285

1 stars
158 downloads
Not rated
GitHub

About

A simple Model Context Protocol server that provides two time-related tools for AI assistants like Claude Desktop: a wait tool to pause execution for a specified number of seconds, and a getdatetime tool to return the current date and time in ISO 8601 format.

Details

Author
Amico1285
GitHub stars
1
Downloads
158
Categories
Other, AI

- Wait tool pauses execution for a configurable number of seconds
- Get datetime tool returns current UTC time in ISO 8601 format
- Maximum wait duration configurable via MCP_WAIT_MAX_DURATION_SECONDS (default 210 seconds)
- Customizable tool description via MCP_WAIT_TOOL_DESCRIPTION
- Written in TypeScript and runs on Node.js 18+
- Supports zero-install usage with npx

Install via npx (recommended, no installation needed), npm global install, or clone and build from source. Configure the server in your Claude Desktop config file (~/.anthropic/config.json on macOS/Linux, %APPDATA%\anthropic\config.json on Windows) using the command "npx mcp-wait-server@latest" and optional environment variables for maximum wait duration and tool description. Restart Claude Desktop to make the tools available.

MCP Wait Server

Simple Model Context Protocol server providing time-related tools for Claude Desktop and other MCP clients:
- wait - Pauses execution for a specified number of seconds, useful when you need to wait for long-running operations to complete
- get_datetime - Returns the current date and time in ISO 8601 format

Implementation

- Written in TypeScript
- Located in src/index.ts (source) and build/index.js (compiled)
- Run with: npm start or directly with node build/index.js

Installation

Option 1: Use with npx (Recommended - No Installation Required)

The simplest approach is to use npx, which runs the package without installing it. Configure Claude Desktop as shown in the "Usage" section below.

Option 2: Install from npm

If you prefer to install the package:

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.