n8n MCP Server
Enables AI assistants to interact with n8n workflow automation instances through the REST API. Supports workflow management, execution control, tag organization, execution history monitoring, and webhook management.
README
n8n MCP Server
MCP (Model Context Protocol) server for n8n workflow automation. This server enables AI assistants like Claude to interact with n8n instances via the REST API.
Features
- 🔄 Workflow Management: List, create, update, and delete workflows
- ▶️ Execution Control: Execute workflows and monitor executions
- 🏷️ Tag Management: Organize workflows with tags
- 📊 Execution History: Access workflow execution history and results
- 🔑 Credential Management: List available credentials (read-only)
- 🌐 Webhook Management: Create and manage webhooks
- 🔍 Search: Search workflows by name or tags
Prerequisites
- Node.js 18 or higher
- n8n instance with API access enabled
- n8n API key
Installation
From npm (when published)
npm install -g n8n-mcp-server
From source
git clone https://github.com/nikolausm/n8n-mcp-server.git
cd n8n-mcp-server
npm install
npm run build
Configuration
Getting your n8n API Key
- Log in to your n8n instance
- Go to Settings → API
- Generate an API key
Configure Claude Desktop
Add the following to your Claude Desktop configuration (claude_desktop_config.json):
{
"mcpServers": {
"n8n": {
"command": "node",
"args": ["/path/to/n8n-mcp-server/dist/index.js"],
"env": {
"N8N_URL": "https://your-n8n-instance.com",
"N8N_API_KEY": "your-api-key-here"
}
}
}
}
For n8n cloud instances, use:
N8N_URL:https://your-subdomain.app.n8n.cloud
Available Tools
Workflow Management
list_workflows- List all workflows with optional filteringget_workflow- Get detailed information about a specific workflowcreate_workflow- Create a new workflow from JSONupdate_workflow- Update an existing workflowdelete_workflow- Delete a workflowactivate_workflow- Activate a workflowdeactivate_workflow- Deactivate a workflow
Execution
execute_workflow- Execute a workflow with optional input dataget_executions- Get execution history with filtering optionsget_execution- Get details of a specific executiondelete_execution- Delete an executionretry_execution- Retry a failed execution
Tags
get_tags- List all available tagscreate_tag- Create a new tagupdate_tag- Update a tagdelete_tag- Delete a tag
Other
get_credentials- List available credentials (names only)search_workflows- Search workflows by name or tagsget_workflow_webhooks- Get webhook URLs for a workflow
Usage Examples
List all active workflows
Assistant: I'll list all your active n8n workflows.
[Uses list_workflows tool with active=true]
Execute a workflow
Assistant: I'll execute the workflow with the data you provided.
[Uses execute_workflow tool with workflowId and data]
Create a new workflow
Assistant: I'll create a new workflow for you.
[Uses create_workflow tool with workflow JSON]
Development
Setup
npm install
Build
npm run build
Test locally
N8N_URL=https://your-instance.com N8N_API_KEY=your-key npm start
Run tests
npm test
Security Notes
- Never commit your API keys
- Use environment variables for sensitive data
- The MCP server has the same permissions as your API key
- Consider using a restricted API key if possible
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
MIT - see LICENSE file
Support
Author
Michael Nikolaus - GitHub
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。