cron-mcp

cron-mcp

Enables scheduling prompts with cron expressions and receiving webhook POSTs to callback URLs.

Category
访问服务器

README

cron-mcp

Built by Shreyas · Shipped by Globalion

Cron-as-a-service MCP. Schedule any prompt on any cron expression; when it fires we POST the job to your callback URL. No LLM in our stack.

Your agent (Claude Desktop, Cursor, a custom script) does the thinking. We just:

  • store the schedule + prompt + your callback URL
  • match minutes against the cron expression
  • POST the job body to your callback, signed with X-Cron-Signature

That's it. Perfect for daily briefings, hourly polls, weekly digests, or anything else that repeats on a fixed schedule and needs to run through an LLM.

Hosted at cron.regiq.in or self-host with the Docker Compose below.

Use it (hosted)

  1. Visit https://cron.regiq.in, sign in with Google or GitHub.

  2. Generate an MCP API key on the dashboard, copy it.

  3. Add to Claude Desktop's claude_desktop_config.json (or Cursor / any MCP client):

    {
      "mcpServers": {
        "cron": {
          "url": "https://cron.regiq.in/api/mcp",
          "headers": {
            "Authorization": "Bearer YOUR_KEY_HERE"
          }
        }
      }
    }
    
  4. Have your agent call schedule_job with a cron expression, a prompt, and the URL you want us to POST to when it fires.

Tools

Tool Purpose
schedule_job(name, cron, prompt, callbackUrl, ...) Create a scheduled prompt.
list_jobs() Return every job owned by the calling key.
get_job(id) One job + the last 20 fire attempts.
update_job(id, ...) Partial update. Set isActive: false to pause.
delete_job(id) Permanent delete.

Webhook payload

When a job fires, we POST:

POST <your callbackUrl>
Content-Type: application/json
X-Cron-Signature: <hex-hmac-sha256-of-body>

{
  "jobId":    "clx...",
  "name":     "daily AI news briefing",
  "prompt":   "summarise the top 5 AI news items from the last 24h",
  "metadata": { ... },
  "firedAt":  "2026-07-16T08:00:00.412Z"
}

Verify the signature by re-hashing the raw body with your shared signing secret (env CRON_WEBHOOK_SIGNING_SECRET) and comparing to the X-Cron-Signature header. Return any 2xx to mark the fire as ok — anything else is logged as a failure and the schedule still advances (so a failing callback won't stop future runs).

Self-host

You'll need:

  • Docker + Compose
  • A Google OAuth client — Cloud Console. Scopes: openid, email, profile. Redirect: <PUBLIC_BASE_URL>/api/auth/callback/google
  • A public HTTPS domain (Cloudflare Tunnel or ngrok http 3015 locally)

No LLM key required. Your callback is where inference happens.

git clone https://github.com/globalion/cron-mcp
cd cron-mcp
cp .env.example .env
# fill NEXTAUTH_SECRET, GOOGLE_*, PUBLIC_BASE_URL, CRON_WEBHOOK_SIGNING_SECRET
docker compose up -d
# open http://localhost:3015

Architecture

  Your agent                                Your callback
     │                                            ▲
     │ schedule_job(cron, prompt,                 │
     │              callback_url)                 │
     ▼                                            │
   ┌──────────────────────────────────────────────────┐
   │  cron-mcp (Hetzner)                              │
   │  - /api/mcp     Bearer-auth JSON-RPC             │
   │    · schedule_job, list, get, update, delete     │
   │  - Postgres: User, ApiKey, Job, JobRun           │
   │  - Scheduler loop (60s tick) — matches cron,     │
   │    POSTs signed webhook to callback_url,         │
   │    logs a JobRun row per fire.                   │
   └──────────────────────────────────────────────────┘
                             │
                             │  POST (signed)
                             ▼
                    Your callback runs the
                    prompt through the LLM +
                    tools and delivers the result.

License

MIT. See LICENSE.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选