@crontinel/mcp-server

@crontinel/mcp-server

Connects AI assistants to Crontinel, enabling natural language queries about cron jobs, queues, Horizon status, and alerts without opening a browser.

Category
访问服务器

README

@crontinel/mcp-server

npm version Node.js License: MIT GitHub stars

An MCP (Model Context Protocol) server that connects AI assistants to Crontinel, the background job monitoring platform for Laravel. It runs as a local stdio process, proxying tool calls from your AI assistant to the Crontinel REST API.

Ask your AI assistant questions like "Did my cron jobs run last night?" or "What's the queue depth right now?" and get answers inline, without opening a browser.

Requirements

Installation

npx -y @crontinel/mcp-server

Or install globally:

npm install -g @crontinel/mcp-server

Configuration

Claude Code

Add to ~/.claude/settings.json (or use the Claude Code settings UI):

{
  "mcpServers": {
    "crontinel": {
      "command": "npx",
      "args": ["-y", "@crontinel/mcp-server"],
      "env": {
        "CRONTINEL_API_KEY": "your-api-key-here"
      }
    }
  }
}

Cursor

Add to ~/.cursor/mcp.json or the project-level .cursor/mcp.json:

{
  "mcpServers": {
    "crontinel": {
      "command": "npx",
      "args": ["-y", "@crontinel/mcp-server"],
      "env": {
        "CRONTINEL_API_KEY": "your-api-key-here"
      }
    }
  }
}

Environment Variables

Variable Required Default Description
CRONTINEL_API_KEY Yes n/a Your Crontinel API key
CRONTINEL_API_URL No https://app.crontinel.com Override the API base URL (self-hosted or local dev)

Available Tools

Tool Description
list_scheduled_jobs List all monitored cron commands with last run status
get_cron_status Last run details for a specific command (exit code, duration, output)
get_queue_status Depth, failed count, and wait time for queues
get_horizon_status Horizon supervisor health snapshot (status, failed/min)
list_recent_alerts Alerts fired in the last N hours
acknowledge_alert Dismiss an active alert by its key
create_alert Create a new alert channel (Slack, email, or webhook)

list_scheduled_jobs

List all monitored cron jobs for an app, with their last run status and timing.

Parameters:

Name Type Required Description
app_slug string Yes App slug from your Crontinel dashboard

Returns: Array of job objects with command, schedule, last_run_at, last_exit_code, last_duration_ms, status (ok / late / failing / never_ran).


get_cron_status

Get the last run result for a specific cron command.

Parameters:

Name Type Required Description
app_slug string Yes App slug
command string Yes The cron command string (e.g. php artisan inspire)

Returns: command, last_run_at, exit_code, duration_ms, output (last 500 chars of stdout/stderr), status.


get_queue_status

Get queue depth, failed count, and oldest pending job age.

Parameters:

Name Type Required Description
app_slug string Yes App slug
queue string No Specific queue name; omit for all queues

Returns: Array of queue objects with name, depth, failed_count, oldest_job_age_seconds.


get_horizon_status

Get a health snapshot of Laravel Horizon: supervisor states, paused/running, failed jobs per minute.

Parameters:

Name Type Required Description
app_slug string Yes App slug

Returns: status (running / paused / inactive), failed_jobs_per_minute, supervisors array with name, status, processes.


list_recent_alerts

List alerts that have fired within the last N hours.

Parameters:

Name Type Required Description
app_slug string Yes App slug
hours number No Look-back window in hours (default: 24)

Returns: Array of alert objects with alert_key, state (firing / resolved), fired_at, resolved_at, message.


acknowledge_alert

Dismiss an active alert so it stops notifying.

Parameters:

Name Type Required Description
app_slug string Yes App slug
alert_key string Yes Alert key (from list_recent_alerts)

Returns: { acknowledged: true, alert_key: "..." } on success.


create_alert

Create a new alert channel for an app. Requires a Pro or Team plan.

Parameters:

Name Type Required Description
app_slug string Yes App slug
type string Yes slack, email, or webhook
config object Yes Channel-specific config (see below)

Config by type:

Type Required fields
slack webhook_url: Incoming Webhook URL
email address: Recipient email address
webhook url: Endpoint URL; optionally secret for HMAC signing

Returns: The new alert channel ID on success.


How It Works

  1. Your AI assistant spawns the MCP server as a local stdio process
  2. The server receives JSON-RPC tool calls over stdin
  3. It forwards each call as an HTTP request to app.crontinel.com/api/mcp with your API key in the Authorization header
  4. The JSON-RPC response is returned over stdout

All tool definitions are declared locally so your AI can inspect them without a network round-trip.

Troubleshooting

401 Unauthorized: Your CRONTINEL_API_KEY is missing or invalid. Check that the env var is set in your MCP config, not your shell profile (MCP servers don't inherit your shell environment).

404 Not Found on a tool call: The app_slug doesn't match any app in your account. Copy the slug from the app URL in the Crontinel dashboard (app.crontinel.com/apps/{slug}).

Tools not showing up in Claude/Cursor: Restart the AI client after updating the MCP config. Most clients only load MCP servers at startup.

npx slow on first run: npx -y downloads the package on first use. Run npm install -g @crontinel/mcp-server once to cache it locally, then change command to crontinel-mcp and remove the args.

Documentation

For the full integration guide, tool reference, and setup walkthroughs:

Ecosystem

Package Description
@crontinel/mcp-server MCP server for AI assistants (this repo)
crontinel/laravel Laravel package that reports the data this server reads
docs.crontinel.com Full documentation

License

MIT

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