Scheduler
MCP Scheduler is a task automation server that lets you schedule shell commands, API calls, AI tasks, and desktop notifications using cron expressions. Built with Model Context Protocol for seamless integration with Claude Desktop and other AI assist
What is Scheduler?
Scheduler is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp scheduler is a task automation server that lets you schedule shell commands, api calls, ai tasks, and desktop notifications using cron expressions. built with model context protocol for seamless i...
MCP Scheduler is a task automation server that lets you schedule shell commands, API calls, AI tasks, and desktop notifications using cron expressions. Built with Model Context Protocol for seamless integration with Claude Desktop and other AI assist
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP Scheduler is a task automation server that lets you sche
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx schedulerConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Scheduler
MCP Scheduler is a task automation server that lets AI assistants schedule and manage recurring or one-off tasks using standard cron expressions. It supports four task types — shell command execution, HTTP API calls, AI content generation (via OpenAI), and desktop notifications — all stored in a local SQLite database and executed on a configurable polling interval. Built with Python and the Model Context Protocol, it integrates with Claude Desktop or any MCP client to let you create, modify, and monitor scheduled tasks entirely through natural language.
Prerequisites
- Python 3.11 or later installed
- uv package manager installed (recommended) or pip
- An OpenAI API key (required only for AI task type)
- An MCP-compatible client such as Claude Desktop
- Git to clone the repository
Clone the repository
Clone the scheduler-mcp repository to a local directory. This server runs from source.
git clone https://github.com/PhialsBasement/scheduler-mcp.git
cd scheduler-mcpCreate a virtual environment and install dependencies
Use uv for fast dependency installation. Activate the virtual environment before running the server.
uv venv
source .venv/bin/activate # macOS/Linux
# or: .venv\Scripts\activate # Windows
uv pip install -r requirements.txtConfigure environment variables
Set the required variables. OPENAI_API_KEY is only needed if you plan to use the AI task type. Other variables have sensible defaults.
export OPENAI_API_KEY="sk-..." # Required for AI tasks
export MCP_SCHEDULER_PORT=8080 # Default: 8080
export MCP_SCHEDULER_TRANSPORT=stdio # 'stdio' or 'sse'
export MCP_SCHEDULER_DB_PATH=scheduler.db # SQLite file pathStart the scheduler server
Run the server with Python. For stdio transport (used with Claude Desktop), the server communicates via stdin/stdout.
python main.pyAdd the server to your MCP client configuration
Add the scheduler to your Claude Desktop config, pointing to the Python interpreter inside the virtual environment and the main.py file.
{
"mcpServers": {
"scheduler": {
"command": "/path/to/scheduler-mcp/.venv/bin/python",
"args": ["/path/to/scheduler-mcp/main.py"],
"env": {
"OPENAI_API_KEY": "sk-...",
"MCP_SCHEDULER_DB_PATH": "/path/to/scheduler-mcp/scheduler.db"
}
}
}
}Scheduler Examples
Client configuration
claude_desktop_config.json entry for the MCP Scheduler server using the local Python virtualenv.
{
"mcpServers": {
"scheduler": {
"command": "/Users/you/scheduler-mcp/.venv/bin/python",
"args": ["/Users/you/scheduler-mcp/main.py"],
"env": {
"OPENAI_API_KEY": "sk-your-openai-key",
"MCP_SCHEDULER_DB_PATH": "/Users/you/scheduler-mcp/scheduler.db",
"MCP_SCHEDULER_TRANSPORT": "stdio"
}
}
}
}Prompts to try
Example prompts for scheduling tasks once the server is connected to Claude Desktop.
- "Schedule a daily database backup at midnight using the command: pg_dump mydb > backup.sql"
- "Create a task to fetch weather data from https://api.weather.com/v1/current every 6 hours."
- "Schedule an AI task to generate a weekly summary report every Monday at 8 AM."
- "Show me all scheduled tasks and their next run times."
- "Disable the weather fetch task without deleting it."
- "Show the execution history for the backup task and tell me if it succeeded."Troubleshooting Scheduler
AI task type fails with 'OpenAI API key not set' error
Set OPENAI_API_KEY in the env block of your MCP client config or as an environment variable before starting the server. The key must be a valid OpenAI key starting with 'sk-'.
Tasks are not executing at the scheduled time
Check MCP_SCHEDULER_CHECK_INTERVAL (default 5 seconds) and MCP_SCHEDULER_EXECUTION_TIMEOUT (default 300 seconds). If the server process is not running continuously (e.g., Claude Desktop restarts it per-session), tasks will not fire between sessions — run the server as a background service instead.
Server exits immediately when started from Claude Desktop
Ensure the command path points to the Python interpreter inside the .venv directory (not the system Python) and that all dependencies were installed in that environment. Run the command manually in a terminal to see error output.
Frequently Asked Questions about Scheduler
What is Scheduler?
Scheduler is a Model Context Protocol (MCP) server that mcp scheduler is a task automation server that lets you schedule shell commands, api calls, ai tasks, and desktop notifications using cron expressions. built with model context protocol for seamless integration with claude desktop and other ai assist It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Scheduler?
Follow the installation instructions on the Scheduler GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Scheduler?
Scheduler works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Scheduler free to use?
Yes, Scheduler is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Scheduler Alternatives — Similar Business Applications Servers
Looking for alternatives to Scheduler? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Scheduler in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Scheduler?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.