Cover image
Try Now
2025-03-01

MCP服务器用于编程性创建和管理N8N工作流程

3 years

Works with Finder

3

Github Watches

42

Github Forks

157

Github Stars

n8n Workflow Builder MCP Server

This project provides an MCP server for managing n8n workflows. It offers functionality to list, create, update, delete, activate, and deactivate workflows through a set of defined tools.

Important:
This version exclusively supports npm for package management and running the server. (npx support will be reintroduced in a future update.)

Requirements

  • Node.js (v14+ recommended)
  • npm

Extensive Installation Guide

1. Clone the Repository

Clone the repository from your preferred source. For example:

git clone https://github.com/makafeli/n8n-workflow-builder.git

Then, navigate to the project directory:

cd /root/n8n-workflow-builder

2. Install Dependencies

Install the necessary dependencies using npm:

npm install

This command will download and install all required packages as defined in the package.json file.

3. Build and Test

For testing and getting the server online, use the following commands:

  • Build the project:
    This compiles the TypeScript files and produces the executable JavaScript in the build directory.

    npm run build
    
  • Start the MCP Server:
    Launch the server using:

    npm start
    

The server will start and connect via stdio. You can check the console to see messages confirming that the server has started correctly.

4. Deployment

For testing purposes and to get the server online, use the build and start commands mentioned above. This basic workflow (install, build, start) is currently the recommended method.

5. Additional Configuration

Server configuration is managed via the cline_mcp_settings.json file. Ensure that the following environment variables are correctly set:

  • N8N_HOST: Your n8n API host URL.
  • N8N_API_KEY: Your n8n API key.

Example configuration in cline_mcp_settings.json:

{
  "n8n-workflow-builder": {
    "command": "node",
    "args": ["/root/n8n-workflow-builder/build/index.js"],
    "env": {
      "N8N_HOST": "https://n8n.io/api/v1/",
      "N8N_API_KEY": "YOUR_N8N_API_KEY_HERE"
    },
    "disabled": false,
    "alwaysAllow": [
      "create_workflow",
      "create_workflow_and_activate",
      "update_workflow",
      "activate_workflow",
      "deactivate_workflow",
      "get_workflow",
      "delete_workflow"
    ],
    "autoApprove": []
  }
}

Available Features

MCP Tools

The following tools are defined in the server and can be accessed through your MCP client:

Workflow Management

  • list_workflows: Lists all workflows from n8n.
  • create_workflow: Creates a new workflow in n8n.
  • get_workflow: Retrieves a workflow by its ID.
  • update_workflow: Updates an existing workflow.
  • delete_workflow: Deletes a workflow by its ID.
  • activate_workflow: Activates a workflow by its ID.
  • deactivate_workflow: Deactivates a workflow by its ID.

Execution Management

  • list_executions: Lists all workflow executions with optional filters.
  • get_execution: Retrieves details of a specific execution by its ID.
  • delete_execution: Deletes an execution by its ID.

MCP Resources

The server also provides the following resources for more efficient context access:

Static Resources

  • /workflows: List of all available workflows in the n8n instance
  • /execution-stats: Summary statistics about workflow executions

Dynamic Resource Templates

  • /workflows/{id}: Detailed information about a specific workflow
  • /executions/{id}: Detailed information about a specific execution

Troubleshooting

  • Ensure you are using npm (this version does not support npx).
  • If you encounter any issues, try cleaning the build directory and rebuilding:
    npm run clean && npm run build
    
  • Verify that your environment variables in cline_mcp_settings.json are correct.

Future Enhancements

  • Reintroduction of npx support.
  • Additional tools and workflow features.
  • Further enhancements to deployment and scaling.

License

This project is licensed under the MIT License.

相关推荐

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Alexandru Strujac
  • Efficient thumbnail creator for YouTube videos

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • Carlos Ferrin
  • Encuentra películas y series en plataformas de streaming.

  • https://zenepic.net
  • Embark on a thrilling diplomatic quest across a galaxy on the brink of war. Navigate complex politics and alien cultures to forge peace and avert catastrophe in this immersive interstellar adventure.

  • https://reddgr.com
  • Delivers concise Python code and interprets non-English comments

  • pontusab
  • 光标与风浪冲浪社区,查找规则和MCP

  • av
  • 毫不费力地使用一个命令运行LLM后端,API,前端和服务。

  • 1Panel-dev
  • 🔥1Panel提供了直观的Web接口和MCP服务器,用于在Linux服务器上管理网站,文件,容器,数据库和LLMS。

  • GeyserMC
  • 与Minecraft客户端/服务器通信的库。

  • Mintplex-Labs
  • 带有内置抹布,AI代理,无代理构建器,MCP兼容性等的多合一桌面和Docker AI应用程序。

  • awslabs
  • AWS MCP服务器 - 将AWS最佳实践直接带入您的开发工作流程的专门MCP服务器

  • WangRongsheng
  • 🧑‍🚀 llm 资料总结(数据处理、模型训练、模型部署、 o1 模型、mcp 、小语言模型、视觉语言模型)|摘要世界上最好的LLM资源。

  • appcypher
  • 很棒的MCP服务器 - 模型上下文协议服务器的策划列表

  • 1Panel-dev
  • 💬MAXKB是一种现成的AI聊天机器人,它集成了检索功能增强的生成(RAG)管道,支持强大的工作流程并提供高级的MCP工具使用功能。

  • chongdashu
  • 使用模型上下文协议(MCP),启用Cursor,Windsurf和Claude Desktop等AI助手客户,以通过自然语言控制虚幻引擎。

    Reviews

    2 (1)
    Avatar
    user_yNtvrXZX
    2025-04-17

    I'm a big fan of the n8n-workflow-builder by makafeli. It's a brilliant tool for automating tasks and workflows seamlessly. The intuitive interface makes it easy for both beginners and experts to set up complex automation. Highly recommended for anyone looking to streamline their workflow processes. Check it out on GitHub!