automation-queue-mcp
automation-queue-mcp
一个让 Claude 这样的 LLM 检查和操控自动化作业队列的 MCP(Model Context Protocol)服务器——通过自然语言列出作业、检查状态、触发新运行、重试失败的作业,并获取整个队列的统计信息。
为什么我要构建这个
在多年领导企业 RPA(通过 AWS Lambda 触发的 UiPath 队列、机器人/机器生命周期、许可证和基础设施管理)平台工程之后,我不断回到同一个问题:如果 LLM 真的能直接操作那个队列,而不是由人类查看仪表板并手动重新触发失败的作业,那会是什么样子?
这个项目是那个想法的通用化、非专有版本——一个 MCP 服务器,暴露任何自动化队列都需要的操作(列出、检查、触发、重试、统计),让 LLM 客户端能够以对话方式推理并管理自动化作业。
它使用内存中的模拟队列,因此无需任何设置即可安全地立即运行和探索。将 job_queue.py 换成真实后端(REST API、数据库、Orchestrator 客户端),即可让它指向真实的自动化环境。
Related MCP server: Hatchet MCP Server
它能做什么
工具 | 描述 |
| 列出队列中的作业,可选按状态过滤( |
| 单个作业的完整详情,包括其执行日志 |
| 为给定工作流触发新作业,可选在特定机器上触发 |
| 将当前处于 |
| 聚合统计——按状态的计数、当前在使用的机器 |
示例交互(通过 Claude)
你: 队列里现在有什么失败的?
Claude: (调用
list_jobs,参数为status_filter="failed") 有两个作业失败了:BOT-VM-02 上的EligibilityCheck_Workflow(已经重试 2 次) 和 BOT-VM-04 上的ExceptionHandling_Workflow(重试 1 次)。要我重试 其中任何一个吗?你: 重试资格检查那个。
Claude: (调用
retry_failed_job,参数为job_id=2) 搞定了——它已回到队列中,现在是第 3 次重试。
快速开始
git clone https://github.com/<your-username>/automation-queue-mcp.git
cd automation-queue-mcp
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt
python server.py将其连接到 Claude Desktop
将服务器添加到你的 Claude Desktop 配置中(模板参见 examples/claude_desktop_config.json):
{
"mcpServers": {
"automation-queue": {
"command": "python",
"args": ["/absolute/path/to/automation-queue-mcp/server.py"]
}
}
}重启 Claude Desktop,上述五个工具就可在对话中使用了。
项目结构
automation-queue-mcp/
├── server.py # MCP server + tool definitions
├── job_queue.py # In-memory mock job queue (swap for a real backend)
├── requirements.txt
├── examples/
│ └── claude_desktop_config.json
└── LICENSE扩展此项目
job_queue.py 中的模拟 JobQueue 类有意与 server.py 中的 MCP 服务器逻辑隔离——要将其连接到真实的自动化系统,你只需要针对实际队列/API 重新实现 JobQueue 的五个方法(list_jobs、get_job、queue_stats、trigger_job、retry_job)即可。MCP 工具层无需更改。
背景
由 John Samuel Jacob David Ravichandran 构建——拥有企业智能自动化、平台工程和医疗保健 RPA 的技术负责人背景。更多信息见 LinkedIn。
许可证
MIT——参见 LICENSE。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI assistants to manage BullMQ Redis-based job queues through natural language, supporting operations like job monitoring, queue control, and multi-instance Redis connections. Users can add, retry, promote, and clean jobs while accessing detailed job logs and queue statistics directly within the assistant.20587MIT
- AlicenseAqualityDmaintenanceEnables monitoring and debugging of Hatchet workflows and jobs through MCP clients like Claude Code. Users can list workflows, track run statuses, query queue metrics, and retrieve job results using natural language commands.62MIT
- FlicenseNot gradedqualityDmaintenanceEnables LLMs to access Jenkins job data, trigger builds, and manage Jenkins tasks through a standardized interface.5
- AlicenseBqualityBmaintenanceProvides AI assistants with full access to Jenkins CI/CD systems, enabling querying, managing, and controlling Jenkins jobs, builds, nodes, and queues through natural language.223111MIT
Related MCP Connectors
Reliable async execution for agent tool calls: schema gating, retries, idempotency, audit trail.
Streamline your Attio workflows using natural language to search, create, update, and organize com…
Live SEO workflow tools for Claude Code, Codex, and AI agents.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/johnSJ1112/automation-queue-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server