mcp-cron
MCP Server that schedule shell command or AI prompt tasks
Documentation
MCP Cron
Model Context Protocol (MCP) server for scheduling and managing tasks through a standardized API. The server provides task scheduling capabilities supporting both shell commands and AI-powered tasks, all accessible via the MCP protocol.
Features
- Schedule shell command or prompt to AI tasks using cron expressions
- AI can have access to MCP servers
- Manage tasks via MCP protocol
- Task execution with command output capture
- Task persistence across restarts (SQLite)
- Multi-instance safe — multiple instances can share the same database without duplicate execution
- Support multiple isolated instances with different `--db-path`
Installation
npm (recommended)
npx -y mcp-cronClaude Code
claude mcp add mcp-cron -- npx -y mcp-cronCursor / Claude Desktop
{
"mcpServers": {
"mcp-cron": {
"command": "npx",
"args": ["-y", "mcp-cron", "--transport", "stdio"]
}
}
}Recommended Configuration
A more complete setup with AI provider, model selection, and sleep prevention:
{
"mcpServers": {
"mcp-cron": {
"command": "npx",
"args": [
"-y", "mcp-cron",
"--transport", "stdio",
"--prevent-sleep",
"--ai-provider", "anthropic",
"--ai-model", "claude-sonnet-4-5-20250929"
],
"env": {
"ANTHROPIC_API_KEY": "your-api-key"
}
}
}
}Using LiteLLM
To route AI tasks through a LiteLLM proxy:
{
"mcpServers": {
"mcp-cron": {
"command": "npx",
"args": [
"-y", "mcp-cron",
"--transport", "stdio",
"--prevent-sleep",
"--ai-base-url", "https://litellm.yourcompany.com",
"--ai-model", "claude-sonnet-4-5-20250929"
],
"env": {
"MCP_CRON_AI_API_KEY": "sk-your-litellm-key"
}
}
}
}> The `--ai-model` value should match a model name in your LiteLLM proxy config. LiteLLM exposes an OpenAI-compatible API, so `--ai-provider` can be omitted (defaults to `openai`). When a custom base URL is set, mcp-cron automatically uses the Chat Completions API instead of the Responses API. The Responses API is only used for direct OpenAI (`api.openai.com`) and Azure OpenAI (`*.openai.azure.com`) endpoints.
> See Command Line Arguments and Environment Variables for all available options.
Building from Source
Prerequisites
- Go 1.24.0 or higher
# Clone the repository
git clone https://github.com/jolks/mcp-cron.git
cd mcp-cron
# Build the application as mcp-cron binary
go build -o mcp-cron cmd/mcp-cron/main.goUsage
The server supports two transport modes:
- HTTP (Streamable HTTP): Default HTTP-based transport for browser and network clients
- stdio: Standard input/output transport for direct piping and inter-process communication
| Client | Config File Location |
|---|---|
| Cursor | `~/.cursor/mcp.json` |
| Claude Desktop (Mac) | `~/Library/Application Support/Claude/claude_desktop_config.json` |
| Claude Desktop (Windows) | `%APPDATA%\Claude\claude_desktop_config.json` |
HTTP (Streamable HTTP)
# Start the server with Streamable HTTP transport (default mode)
# Default to localhost:8080
./mcp-cron
# Start with custom address and port
./mcp-cron --address 127.0.0.1 --port 9090Config file example
{
"mcpServers": {
"mcp-cron": {
"url": "http://localhost:8080"
}
}
}stdio
The stdio transport is particularly useful for:
- Direct piping to/from other processes
- Integration with CLI tools
- Testing in environments without HTTP
- Docker container integration
Upon starting Cursor IDE and Claude Desktop, it will automatically start the server
Config file example
{
"mcpServers": {
"mcp-cron": {
"command": "/mcp-cron",
"args": ["--transport", "stdio"]
}
}
}Command Line Arguments
The following command line arguments are supported:
| Argument | Description | Default |
|---|---|---|
| `--address` | The address to bind the server to | `localhost` |
| `--port` | The port to bind the server to | `8080` |
| `--transport` | Transport mode: `http` or `stdio` | `http` |
| `--log-level` | Logging level: `debug`, `info`, `warn`, `error`, `fatal` | `info` |
| `--log-file` | Log file path | stdout |
| `--version` | Show version information and exit | `false` |
| `--ai-provider` | AI provider: `openai` or `anthropic` | `openai` |
| `--ai-base-url` | Custom base URL for OpenAI-compatible endpoints (e.g. Ollama, vLLM, Groq, LiteLLM) | Not set |
| `--ai-model` | AI model to use for AI tasks | `gpt-4o` |
| `--ai-max-iterations` | Maximum iterations for tool-enabled AI tasks | `20` |
| `--mcp-config-path` | Path to MCP configuration file | `~/.cursor/mcp.json` |
| `--db-path` | Path to SQLite database for result history | `~/.mcp-cron/results.db` |
| `--prevent-sleep` | Prevent system from sleeping while mcp-cron is running (macOS and Windows) | `false` |
| `--poll-interval` | How often to check for due tasks | `1s` |
Environment Variables
The following environment variables are supported:
| Environment Variable | Description | Default |
|---|---|---|
| `MCP_CRON_SERVER_ADDRESS` | The address to bind the server to | `localhost` |
| `MCP_CRON_SERVER_PORT` | The port to bind the server to | `8080` |
| `MCP_CRON_SERVER_TRANSPORT` | Transport mode: `http` or `stdio` | `http` |
| `MCP_CRON_SERVER_NAME` | Deprecated — ignored; the server name is fixed to ensure self-reference detection works correctly | - |
| `MCP_CRON_SERVER_VERSION` | Deprecated — ignored; version is set at build time via ldflags | - |
| `MCP_CRON_SCHEDULER_DEFAULT_TIMEOUT` | Default timeout for task execution | `10m` |
| `MCP_CRON_LOGGING_LEVEL` | Logging level: `debug`, `info`, `warn`, `error`, `fatal` | `info` |
| `MCP_CRON_LOGGING_FILE` | Log file path | stdout |
| `MCP_CRON_AI_PROVIDER` | AI provider: `openai` or `anthropic` | `openai` |
| `MCP_CRON_AI_BASE_URL` | Custom base URL for OpenAI-compatible endpoints (e.g. Ollama, vLLM, Groq, LiteLLM) | Not set |
| `MCP_CRON_AI_API_KEY` | Generic fallback API key (used when provider-specific key is not set) | Not set |
| `OPENAI_API_KEY` | OpenAI API key for AI tasks | Not set |
| `ANTHROPIC_API_KEY` | Anthropic API key for AI tasks | Not set |
| `MCP_CRON_ENABLE_OPENAI_TESTS` | Enable OpenAI integration tests | `false` |
| `MCP_CRON_AI_MODEL` | LLM model to use for AI tasks | `gpt-4o` |
| `MCP_CRON_AI_MAX_TOOL_ITERATIONS` | Maximum iterations for tool-enabled tasks | `20` |
| `MCP_CRON_MCP_CONFIG_FILE_PATH` | Path to MCP configuration file | `~/.cursor/mcp.json` |
| `MCP_CRON_STORE_DB_PATH` | Path to SQLite database for result history | `~/.mcp-cron/results.db` |
| `MCP_CRON_PREVENT_SLEEP` | Prevent system from sleeping while mcp-cron is running (macOS and Windows) | `false` |
| `MCP_CRON_POLL_INTERVAL` | How often to check for due tasks (Go duration format) | `1s` |
Sleep Prevention
On laptops, the system may go to sleep and prevent scheduled tasks from running on time. Use the `--prevent-sleep` flag to keep the system awake while mcp-cron is running:
mcp-cron --prevent-sleep --transport stdioOr via environment variable:
MCP_CRON_PREVENT_SLEEP=true mcp-cron --transport stdio| Platform | Mechanism | Notes |
|---|---|---|
| macOS | `caffeinate` | Prevents idle sleep; automatically cleans up on exit |
| Windows | `SetThreadExecutionState` | Prevents idle sleep; automatically cleans up on exit |
| Linux | Not supported | Linux servers typically do not auto-sleep |
> Note: This prevents idle sleep only. It does not prevent sleep from closing the laptop lid or pressing the power button.
Logging
When running with the default HTTP transport, logs are output to the console.
When running with stdio transport, logs are redirected to a `mcp-cron.log` log file to prevent interference with the JSON-RPC protocol:
- Log file location: Same location as `mcp-cron` binary.
- Task outputs, execution details, and server diagnostics are written to this file.
- The stdout/stderr streams are kept clean for protocol messages only.
Available MCP Tools
The server exposes several tools through the MCP protocol:
1. `list_tasks` - Lists all tasks (scheduled and on-demand)
2. `get_task` - Gets a specific task by ID
3. `add_task` - Adds a new shell command task (provide `schedule` for recurring, or omit for on-demand)
4. `add_ai_task` - Adds a new AI (LLM) task with a prompt (provide `schedule` for recurring, or omit for on-demand)
5. `add_http_task` - Adds a new HTTP (webhook) task that issues an HTTP request to a `url` (provide `schedule` for recurring, or omit for on-demand)
6. `update_task` - Updates an existing task
7. `remove_task` - Removes a task by ID
8. `run_task` - Executes a task by ID, waits for completion, and returns the result (for on-demand tasks or ad-hoc runs of scheduled tasks)
9. `enable_task` - Enables a task so it runs on its schedule or can be triggered via `run_task`
10. `disable_task` - Disables a task so it stops running and cannot be triggered
11. `get_task_result` - Gets execution results for a task (latest by default, or recent history with `limit`)
12. `query_task_result` - Runs a read-only SQL query against the database (SELECT only, capped at 1000 rows)
Task Format
Tasks have the following structure:
{
"id": "task_a3f7b2c9e1d04f68",
"name": "Example Task",
"schedule": "0 */5 * * * *",
"command": "echo 'Task executed!'",
"prompt": "Analyze yesterday's sales data and provide a summary",
"type": "shell_command",
"description": "An example task that runs every 5 minutes",
"enabled": true,
"lastRun": "2025-01-01T12:00:00Z",
"nextRun": "2025-01-01T12:05:00Z",
"status": "completed",
"createdAt": "2025-01-01T00:00:00Z",
"updatedAt": "2025-01-01T12:00:00Z"
}The `type` field can be `shell_command` (default), `AI`, or `http`. The fields that apply depend on the type:
- `shell_command` — `command`: the shell command to execute.
- `AI` — `prompt`: what the AI should do.
- `http` — `url` (required), `method` (defaults to `POST`), `headers` (JSON object of string→string), and `body` (request body string). Created via `add_http_task`.
For HTTP tasks, the result row reuses the existing columns:
| Result field | Meaning for HTTP tasks |
|---|---|
| `exit_code` | HTTP status code (0 if no response was received) |
| `output` | Response body preview (capped at 8 KiB, suffixed `... (truncated)`) |
| `error` | Transport error, build-request error, or `non-2xx status: N ` |
| `duration` | Round-trip latency |
| `url` | The request URL |
This keeps `query_task_result` queries uniform — e.g. `SELECT COUNT(*) FROM results WHERE task_id='x' AND exit_code >= 200 AND exit_code < 300` counts successful HTTP calls.
Scheduled vs on-demand tasks:
- Scheduled: Provide a `schedule` (cron expression) — the task runs automatically on that schedule.
- On-demand: Omit `schedule` — the task sits idle until triggered via `run_task`.
`run_task` also works on scheduled tasks for ad-hoc execution outside their normal schedule. After execution, scheduled tasks resume their normal schedule; on-demand tasks return to idle.
Task Status
The tasks can have the following status values:
- `pending` - Task has not been run yet
- `running` - Task is currently running
- `completed` - Task has successfully completed
- `failed` - Task has failed during execution
- `disabled` - Task is disabled and won't run on schedule
Cron Expression Format
Cron expressions are required for scheduled tasks and omitted for on-demand tasks. The scheduler uses the github.com/robfig/cron/v3 library for parsing. The format includes seconds:
┌───────────── second (0 - 59) (Optional)
│ ┌───────────── minute (0 - 59)
│ │ ┌───────────── hour (0 - 23)
│ │ │ ┌───────────── day of the month (1 - 31)
│ │ │ │ ┌───────────── month (1 - 12)
│ │ │ │ │ ┌───────────── day of the week (0 - 6) (Sunday to Saturday)
│ │ │ │ │ │
│ │ │ │ │ │
* * * * * *Examples:
- `0 */5 * * * *` - Every 5 minutes (at 0 seconds)
- `0 0 * * * *` - Every hour
- `0 0 0 * * *` - Every day at midnight
- `0 0 12 * * MON-FRI` - Every weekday at noon
Development
Building
go build -o mcp-cron cmd/mcp-cron/main.goTesting
See docs/testing.md for the full testing guide, including integration tests and AI task tests.
Acknowledgments
- modelcontextprotocol/go-sdk - Official Go SDK for the Model Context Protocol
- robfig/cron - Cron expression parsing for Go
Frequently asked questions
What is mcp-cron?
mcp-cron is MCP Server that schedule shell command or AI prompt tasks
How do I install mcp-cron?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-cron open source?
Yes — it is hosted on GitHub at https://github.com/jolks/mcp-cron and has 13 stars.
Related MCP tools
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth! Python-based implementation. Trusted by 11000+ developers.
An MCP server that allows MCP clients like Claude Desktop or Cursor to perform actions in the Unity Editor C#-based implementation.
An official Qdrant Model Context Protocol (MCP) server implementation Python-based implementation. Trusted by 1000+ developers.
A middleware to provide an openAI compatible endpoint that can call MCP tools Python-based implementation. Trusted by 800+ developers.
Shell and coding agent on claude desktop app for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.
Vibetest MCP - automated QA testing using Browser-Use agents Python-based implementation. Trusted by 500+ developers. Trusted by 500+ developers.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP