Skip to main content
Glama
enesjakozh
AgentsWorkingTogether

mcp-sleep

by AgentsWorkingTogether
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Sleep MCP Server

This MCP server attempts to pause execution for a specified duration to control the flow of your agents. Enhance your automation by introducing timed delays, ensuring tasks are executed in the desired sequence. Ideal for managing workflows that require waiting periods between actions.

Setup

Installation

Using MCP package managers

Smithery

To install Sleep MCP for Claude Desktop automatically via Smithery:

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

mcp-get

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

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

Prerequisites

MCP is still very new and evolving, we recommend following the MCP documentation to get the MCP basics up and running.

You'll need:

Configuration

1. Configure Claude Desktop

Create the following file depending on your OS:

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

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

Paste this template in the file

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

Optionally, it replace <MCP_SLEEP_TIMEOUT> with your timeout ( maximum time allowed to wait, default 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 by running the following command:

uvx mcp-sleep --transport sse

This mode is useful to integrate with an MCP client that supports SSE (like a web app).

Related MCP server: Treehole MCP Server

Tools

  1. sleep

    • Pause execution for a specified duration to control the flow of your agents.

    • Inputs:

      • seconds (number, max timeout config value): Seconds it will take me to tell you to continue

    • Returns: You will receive the sentence after {seconds} "You can continue to do your task after you've been waiting {seconds} seconds". If you enter a waiting time greater than the maximum time the result will be "My configuration does not allow me to make you wait more than {ctx.sleep.config.timeout} seconds"

Usage with Claude Desktop

To use this with Claude Desktop, add the following to your claude_desktop_config.json:

Docker

{
  "mcpServers": {
    "mcp-sleep": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "MCP_SLEEP_TIMEOUT",
        "mcp/sleep"
      ],
      "env": {
        "MCP_SLEEP_TIMEOUT": "<MCP_SLEEP_TIMEOUT>"
      }
    }
  }
}

Development

Config

If you are working locally add two environment variables to a .env file in the root of the repository:

MCP_SLEEP_TIMEOUT=

For local development, update your Claude Desktop configuration:

{
  "mcpServers": {
      "mcp-sleep_local": {
          "command": "uv",
          "args": [
              "run",
              "--directory",
              "/path/to/your/mcp-sleep",
              "run",
              "mcp-sleep"
          ]
      }
  }
}
"mcpServers": {
  "mcp-sleep": {
    "command": "uvx",
    "args": [
      "mcp-sleep"
    ]
  }
}

Building and Publishing

To prepare the package for distribution:

  1. Sync dependencies and update lockfile:

uv sync

  1. Build package distributions:

uv build

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

  1. Publish to PyPI:

uv publish

Note: You'll 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 over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

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

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

Available Tools

1 tool
sleepC

If you need to wait for a few seconds to continue with the task you are performing .

ParametersJSON Schema
NameRequiredDescriptionDefault
secondsYesseconds it will take me to tell you to continue.

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions waiting behavior but omits key details: whether it blocks execution, if it's synchronous/asynchronous, error handling, or side effects. The phrase 'tell you to continue' hints at notification but is ambiguous. For a tool with no annotation coverage, this leaves significant behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's function. It's appropriately sized for a simple tool, with no redundant or verbose phrasing. However, it could be more front-loaded by starting with the core action (e.g., 'Pauses execution for a specified duration').

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (one parameter, no output schema, no annotations), the description is minimally adequate. It covers the basic purpose but lacks details on behavior, return values, or error cases. With no output schema, it should ideally hint at what happens after waiting (e.g., resumes task). It's complete enough for a simple tool but has room for improvement.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with the parameter 'seconds' well-documented in the schema (type, range, purpose). The description adds no parameter-specific information beyond what the schema provides, so it meets the baseline of 3 for high schema coverage without compensating value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool's purpose as waiting/pausing execution ('wait for a few seconds'), which is clear but somewhat vague. It doesn't specify what resource or system it operates on, and with no sibling tools, differentiation isn't needed. The description avoids tautology by explaining function rather than just restating the name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides implied usage context ('to continue with the task you are performing'), suggesting it's for pacing or timing in workflows. However, it lacks explicit guidance on when to use vs. alternatives (though none exist), prerequisites, or specific scenarios. The guidance is functional but minimal.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observedsleep
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'sleep' has a single, clear purpose that cannot be confused with any other tool in this set.

Naming Consistency5/5

There is only one tool name, so it inherently follows a consistent pattern. The name 'sleep' is a simple verb that clearly describes the tool's function without any naming conflicts or inconsistencies.

Tool Count2/5

A single tool is too few for most practical server purposes, as it severely limits functionality and scope. While the tool 'sleep' might be useful in specific contexts, a server with only one tool typically feels incomplete and under-scoped for agent workflows.

Completeness1/5

The server's purpose appears to be time-based operations, but with only a 'sleep' tool, it is severely incomplete. There are obvious gaps, such as tools for scheduling, timing, or other time-related functions, making the surface inadequate for any meaningful domain coverage.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Wait Timer Server

    199-mcp
    A
    license
    A
    quality
    D
    maintenance
    Provides a simple 'wait' tool that introduces deliberate pauses into workflows executed by MCP clients, allowing time for asynchronous operations to complete before proceeding to the next step.
    1
    13 npm
    1
    MIT

  • Treehole MCP Server

    jeffkit
    A
    license
    B
    quality
    C
    maintenance
    Provides tools for AI agents to take timed rest breaks and vent their thoughts to receive emotional support during complex tasks. It enables developers to implement structured delays while offering a psychological sanctuary for simulated silicon-based life.
    2
    13 npm
    4
    MIT

  • LoopIn MCP Server

    nicholasemccormick
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to pause execution at critical decision points and request human review before proceeding. Provides tools for creating interrupts, polling for decisions, and managing approvals through a simple REST API interface.
    4 npm
    MIT

  • mcp-wait

    AaLexUser
    A
    license
    Not graded
    quality
    D
    maintenance
    Provides a wait tool for AI agents to pause execution until a time duration elapses or a process terminates, useful for polling and waiting for builds/deployments.
    5 npm
    MIT