n8n-workflow-downloader-mcp
An MCP server that enables AI agents to download n8n workflows from URLs.
README
n8n Workflow Downloader MCP Server
An MCP (Model Context Protocol) server that enables AI agents to download n8n workflows from URLs.
Features
- Download n8n workflows from URLs like
https://n8n.io/workflows/3442 - Returns the complete workflow JSON structure
- Includes metadata (workflow ID, name, URL)
- Handles errors gracefully
Installation
As a global npm package
npm install -g n8n-workflow-downloader-mcp
For development
git clone https://github.com/andrewlwn77/n8n-workflow-downloader-mcp.git
cd n8n-workflow-downloader-mcp
npm install
npm run build
Usage
With Claude Desktop or other MCP clients
Add to your MCP configuration:
Using npx (recommended):
{
"mcpServers": {
"n8n-workflow-downloader": {
"command": "npx",
"args": ["n8n-workflow-downloader-mcp"],
"transport": {
"type": "stdio"
},
"env": {
"PUPPETEER_EXECUTABLE_PATH": "/opt/google/chrome/google-chrome"
}
}
}
}
If installed globally via npm:
{
"mcpServers": {
"n8n-workflow-downloader": {
"command": "n8n-workflow-downloader",
"transport": {
"type": "stdio"
},
"env": {
"PUPPETEER_EXECUTABLE_PATH": "/opt/google/chrome/google-chrome"
}
}
}
}
If installed locally or from source:
{
"mcpServers": {
"n8n-workflow-downloader": {
"command": "node",
"args": ["./path/to/build/index.js"],
"transport": {
"type": "stdio"
},
"env": {
"PUPPETEER_EXECUTABLE_PATH": "/opt/google/chrome/google-chrome"
}
}
}
}
Environment Variables
PUPPETEER_EXECUTABLE_PATH(optional): Path to Chrome/Chromium executable- If not set, Puppeteer will use its bundled Chromium
- Useful for systems with Chrome installed in non-standard locations
- Example:
/opt/google/chrome/google-chrome,/usr/bin/chromium-browser
Available Tools
download_n8n_workflow
Downloads an n8n workflow from a given URL.
Input:
url(string, required): The n8n workflow URL (e.g., https://n8n.io/workflows/3442)
Output:
workflow: The complete n8n workflow JSON objectmetadata: Object containing:id: The workflow IDname: The workflow nameurl: The original URL
Example usage in Claude:
Please download the n8n workflow from https://n8n.io/workflows/3442
Development
# Install dependencies
npm install
# Build TypeScript
npm run build
# Watch mode for development
npm run dev
# Run tests
npm test
# Run specific test suites
npm run test:unit # Unit tests only
npm run test:integration # Integration tests only
# Run tests in watch mode
npm run test:watch
# Generate test coverage report
npm run test:coverage
# Test the server manually (for debugging/development)
node test-server.js
Testing
The project includes comprehensive test coverage:
-
Unit Tests (
tests/unit/): Test individual modules in isolation- Downloader module validation and error handling
- URL parsing and validation
- Mock puppeteer interactions
-
Integration Tests (
tests/integration/): Test the complete MCP server- Server initialization
- Tool listing and discovery
- End-to-end workflow download simulation
- Error handling and validation
Run npm test to execute all tests, or use the specific test commands listed above.
Manual Testing
The test-server.js script provides a quick way to manually test the MCP server:
- Initializes the server
- Lists available tools
- Demonstrates a tool call
- Shows real-time server output
This is useful for debugging and development, complementing the automated test suite.
Technical Details
- Uses Puppeteer to automate the workflow download process
- Intercepts clipboard operations to capture workflow JSON
- Built with TypeScript and the official MCP SDK
- Implements stdio transport for local communication
- Supports custom Chrome/Chromium executable paths via
PUPPETEER_EXECUTABLE_PATH
Requirements
- Node.js 16+
- Chrome/Chromium (for Puppeteer)
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。