MCP.so
Sign In

MCP Cron

@jolks

Basic information

Category

Other

License

NOASSERTION

Transports

stdio

Author

jolks

About MCP Cron

MCP server for scheduling and running AI prompts, HTTP/webhook requests, and shell commands

MCP Cron config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-cron": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-cron"
      ]
    }
  }
}

MCP Cron tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is MCP Cron?

MCP Cron is a Model Context Protocol server for scheduling and managing tasks through a standardized API. It supports shell commands, AI-powered tasks, and HTTP webhook tasks, with task persistence across restarts via SQLite. It's intended for developers and AI agents that need to schedule recurring or on-demand work.

How to use MCP Cron?

Install via npx -y mcp-cron and configure it in your MCP client's config file (e.g., ~/.cursor/mcp.json or Claude Desktop's config). The server supports two transport modes: HTTP (Streamable HTTP, default) and stdio. Key command-line arguments include --transport, --ai-provider, --ai-model, --db-path, and --prevent-sleep.

Key features of MCP Cron

  • Schedule shell command, AI, or HTTP tasks using cron expressions
  • AI tasks can use other MCP servers via a config file
  • Manage tasks (add, list, run, update, remove) via MCP protocol
  • Task execution with output capture and result history
  • Task persistence across restarts using SQLite
  • Multi-instance safe — multiple instances can share the same database

Use cases of MCP Cron

  • Schedule recurring system administration scripts or maintenance commands
  • Have an AI agent periodically analyze data and provide summaries
  • Trigger HTTP webhooks on a cron schedule for API polling or health checks
  • Run on-demand tasks (without a schedule) for ad-hoc execution via run_task

Frequently asked questions

1

What's the difference between scheduled and on-demand tasks?

Scheduled tasks include a cron expression and run automatically on that schedule. On-demand tasks omit the schedule and sit idle until triggered via the `run_task` tool.

2

What transports does MCP Cron support?

It supports HTTP (Streamable HTTP, the default) and stdio. HTTP is for browser/network clients; stdio is for direct piping and inter-process communication.

3

How does sleep prevention work?

On macOS and Windows, the `--prevent-sleep` flag prevents the system from going idle while MCP Cron is running. It uses `caffeinate` on macOS and `SetThreadExecutionState` on Windows. Linux is not supported for sleep prevention.

4

What database does MCP Cron use for persistence?

It uses a local SQLite database. The default path is `~/.mcp-cron/results.db`, configurable with the `--db-path` flag or `MCP_CRON_STORE_DB_PATH` environment variable.

5

How do I configure AI providers for AI tasks?

Use `--ai-provider` (openai or anthropic) and `--ai-model` flags, or their corresponding environment variables. API keys are set via `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, or the generic `MCP_CRON_AI_API_KEY`. A custom base URL (`--ai-base-url`) supports OpenAI-compatible endpoints like LiteLLM.

Comments

More Other MCP servers