N8n Assistant

🚀 n8n Assistant

This project offers a Multi-Channel Platform (MCP) server to create an assistant integrated with n8n. The assistant can search n8n documentation, example workflows, and community forums.

🚀 Quick Start

To start using the n8n Assistant, you first need to install it. You can choose either automatic installation via Smithery or manual installation. After installation, you can start the assistant and query it for n8n - related information.

✨ Features

• Web Search: Searches n8n documentation, workflows, and community forums based on a specific query.
• HTML Content Fetching: Uses BeautifulSoup to extract the main content from search results.
• Asynchronous Processing: Performs HTTP requests asynchronously, providing faster response times.

📦 Installation

Installing via Smithery

To install n8n - assistant for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @onurpolat05/n8n-assistant --client claude

Manual Installation

1. Clone this repository:

   git clone <repository-url>
   cd <repository-directory>
   

2. Install the required dependencies:

   pip install -r requirements.txt
   

3. Create a .env file and add the necessary API keys:

   SERPER_API_KEY=your_api_key_here
   

💻 Usage Examples

Basic Usage

To start the assistant, run the following command:

uvicorn main:app --reload

Then, you can query the assistant for information related to n8n like this:

await get_n8n_info("HTTP Request node", "docs")

Advanced Usage

This project uses the n8n - asistans MCP server. The server is started with the following command:

{
    "mcpServers": {
        "n8n-asistans": {
            "command": "uv",
            "args": [
                "--directory",
                "/n8n-assistant",
                "run",
                "main.py"
            ],
            "env":{
                "SERPER_API_KEY": "*********"
            }
        }
    }
}

🤝 Contributing

If you would like to contribute, please create a pull request or report issues.

📄 License

This project is licensed under the MIT License.