MCP Sleep

🚀 Sleep MCP Server

This MCP server attempts to pause execution for a specified time to control the flow of agents. Enhance your automation by introducing timed delays and ensure tasks are executed sequentially. It's very useful for workflows that require operations between waiting periods.

🚀 Quick Start

📦 Installation

Using MCP Package Managers

Smithery

To automatically install Sleep MCP for Claude Desktop via Smithery:

npx @smithery/cli install @AgentsWorkingTogether/mcp-sleep --client claude

mcp-get

You can install the Sleep MCP server via mcp-get:

npx @michaellatman/mcp-get@latest install mcp-sleep

Prerequisites

MCP is still new and evolving. We recommend following the MCP documentation to understand the basics of MCP.

You need:

• Claude Desktop
• uv

Configuration

1. Configure Claude Desktop

Create the following file depending on your operating system:

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json

On Windows: %APPDATA%/Claude/claude_desktop_config.json%

Paste the following template into the file:

{
    "mcpServers": {
        "mcp-sleep": {
            "command": "uvx",
            "args": [
                "mcp-sleep"
            ],
        }
    }
}

Optionally, replace <MCP_SLEEP_TIMEOUT> with your timeout value (maximum allowed waiting time, default is 60 seconds):

{
    "mcpServers": {
        "mcp-sleep": {
            "command": "uvx",
            "args": [
                "mcp-sleep"
            ],
            "env": {
                "MCP_SLEEP_TIMEOUT": "<MCP_SLEEP_TIMEOUT>"
            }
        }
    }
}

2. Restart Claude Desktop

SSE Mode

Alternatively, you can run the MCP server in SSE mode with the following command:

uvx mcp-sleep --transport sse

This mode is very useful for integrating MCP clients that support SSE, such as web applications.

💻 Usage Examples

Basic Usage

The sleep tool in this server can pause execution for a specified time to control the agent's flow.

sleep 5
# Wait for 5 seconds and then continue

Details

• Input: <duration> is a non - negative integer or floating - point number representing the waiting time in seconds.
• Output: This operation does not return any value after completion.

🔧 Building and Publishing

To prepare the distribution package:

1. Synchronize dependencies and update the lock file:

uv sync

2. Build the distribution package:

uv build

This will create source and wheel distributions in the dist/ directory.

3. Publish to PyPI:

uv publish

Note: You need to set PyPI credentials via environment variables or command flags:

• Token: --token or UV_PUBLISH_TOKEN
• Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Docker Build

docker build -t mcp/sleep -f Dockerfile .

🐞 Debugging

Since MCP servers run via standard input and output, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can start the MCP Inspector with the following command:

npx @modelcontextprotocol/inspector uv --directory /path/to/your/mcp-sleep run mcp-sleep

After starting, the inspector will display a URL that you can access in your browser to start debugging.