Python scheduler library · MCP-native · AGPL-3.0

Task scheduling
for AI agents.

schedulermcp is a modular Python library for scheduling tasks in AI agent pipelines. Cron jobs, intervals, one-shot delays, event-driven watch triggers. Webhook notifications, kernel execution, SQLite persistence.

agent_scheduler.py
from schedulermcp import SchedulerFactory

scheduler = SchedulerFactory.default()
scheduler.start()

await scheduler.schedule(
    goal="Generate daily analytics report",
    job_type="cron",
    cron="0 9 * * 1-5",
    webhook_url="https://api.example.com/reports",
)

await scheduler.schedule(
    goal="Send welcome email in 5 minutes",
    job_type="once",
    delay_seconds=300,
)

from schedulermcp.mcp_server import SchedulerMCPServer
SchedulerMCPServer(scheduler).run()
Cron schedulingWebhook notifications
MCP stdio
4 job types
3 executors
MCP-native
SQLite persistence
Python 3.11+

Everything your agent needs
to schedule and automate

Cron Scheduling

5-field cron syntax — wildcards *, steps */N, ranges N-M and lists N,M. Recurring jobs with auto-computed next run.

5-field cronauto next_run

Interval Jobs

Repeat tasks at fixed intervals with failure tracking and auto-pause after consecutive errors.

fixed intervalauto-retry

One-shot Delays

Fire-and-forget tasks with a delay. Run once after N seconds, or at an absolute datetime.

delay_secondsrun_at

Kernel Execution

Execute scheduled jobs via kernelmcp. AI-powered task execution with full ReAct reasoning.

ReAct enginekernelmcp

Webhook Notifications

Send HTTP POST notifications when jobs fire. Track results, timing, and errors automatically.

HTTP POSTJSON payload

SQLite Persistence

Persist jobs across restarts. Zero-config file-based database. In-memory store also available.

SQLiteInMemory

MCP-Native

9 MCP tools: schedule_task, list_schedules, get_job, cancel_schedule, pause_schedule, resume_schedule, and more.

stdio

Zero Config Start

SchedulerFactory.default() works without any external service. Add SQLite and webhooks as you scale.

default()create()

Install once.
Schedule reliably.

1

Install

One pip install. Zero dependencies to start.

pip install mcpaisuite-schedulermcp
2

Schedule

Create jobs with goal, type, and timing. Scheduler computes next_run and persists.

await scheduler.schedule( goal="Daily report", job_type="cron", cron="0 9 * * *", )
3

Execute

Background loop checks for due jobs every tick. Executors handle the work.

scheduler.start()
4

Deploy

Expose as MCP server, embed in your agent, or run standalone.

SchedulerMCPServer(scheduler).run()

Four job types,
one for each cadence

TypeDescriptionRepeats
onceOne-shot — fire once after delay or at absolute timeNo
cronCron — recurring via cron expressionYes
intervalInterval — repeat every N secondsYes
watchWatch — event-driven, fires when shell command output matches conditionYes

Ready to give your agent
time-based superpowers?

Read the docs Star on GitHub