n8n MCP Server

n8n MCP Server

Enables AI assistants to manage n8n workflows and executions, including creating, updating, deleting, activating, deactivating, and executing workflows, as well as listing and retrieving execution details.

Category
访问服务器

README

n8n MCP Server

A Model Context Protocol (MCP) server for managing n8n workflows. This server enables AI assistants to interact with your n8n instance to create, update, delete, monitor, and control workflows and executions.

Features

Workflow Management

  • List workflows - Get all workflows with optional filtering by active status
  • Get workflow - Retrieve detailed information about a specific workflow
  • Create workflow - Create new workflows programmatically
  • Update workflow - Modify existing workflow configurations
  • Delete workflow - Remove workflows from your n8n instance

Workflow Control

  • Activate workflow - Enable a workflow to run on triggers
  • Deactivate workflow - Disable a workflow

Workflow Execution

  • Execute workflow - Manually trigger a workflow execution
  • List executions - View execution history with optional workflow filtering
  • Get execution - Retrieve detailed execution information including results
  • Delete execution - Remove execution records

Prerequisites

  • Node.js 18 or higher
  • n8n instance (self-hosted or cloud)
  • n8n API key

Installation

  1. Clone this repository:
git clone <repository-url>
cd n8n-mcp
  1. Install dependencies:
npm install
  1. Build the server:
npm run build

Configuration

Generate n8n API Key

  1. Log in to your n8n instance
  2. Go to Settings > n8n API
  3. Click Create an API Key
  4. Copy the generated API key

Environment Variables

Set the following environment variables:

export N8N_BASE_URL="https://your-n8n-instance.com"
export N8N_API_KEY="your-api-key-here"

For n8n cloud:

export N8N_BASE_URL="https://your-instance.app.n8n.cloud"

For self-hosted:

export N8N_BASE_URL="http://localhost:5678"

Usage with Claude Desktop

Add this server to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "n8n": {
      "command": "node",
      "args": ["/absolute/path/to/n8n-mcp/build/index.js"],
      "env": {
        "N8N_BASE_URL": "https://your-n8n-instance.com",
        "N8N_API_KEY": "your-api-key-here"
      }
    }
  }
}

Available Tools

Workflow Management

list_workflows

List all workflows with optional active status filter.

Parameters:

  • active (boolean, optional): Filter by active status

Example:

List all active workflows

get_workflow

Get detailed information about a specific workflow.

Parameters:

  • id (string, required): Workflow ID

Example:

Get workflow with ID "123"

create_workflow

Create a new workflow.

Parameters:

  • name (string, required): Workflow name
  • nodes (array, required): Workflow nodes configuration
  • connections (object, optional): Node connections
  • settings (object, optional): Workflow settings

Example:

Create a simple workflow named "Test Workflow"

update_workflow

Update an existing workflow.

Parameters:

  • id (string, required): Workflow ID
  • name (string, optional): New workflow name
  • nodes (array, optional): Updated nodes
  • connections (object, optional): Updated connections
  • settings (object, optional): Updated settings

delete_workflow

Delete a workflow.

Parameters:

  • id (string, required): Workflow ID

Workflow Control

activate_workflow

Activate a workflow to enable trigger-based execution.

Parameters:

  • id (string, required): Workflow ID

deactivate_workflow

Deactivate a workflow.

Parameters:

  • id (string, required): Workflow ID

Execution Management

execute_workflow

Manually execute a workflow.

Parameters:

  • id (string, required): Workflow ID

list_executions

List workflow executions.

Parameters:

  • workflowId (string, optional): Filter by workflow ID

get_execution

Get detailed execution information.

Parameters:

  • id (string, required): Execution ID

delete_execution

Delete an execution record.

Parameters:

  • id (string, required): Execution ID

Development

Watch mode

npm run watch

Build

npm run build

Troubleshooting

API Key Issues

  • Ensure your API key is valid and has the necessary permissions
  • For n8n Cloud, you need a paid plan to use the API

Connection Issues

  • Verify the N8N_BASE_URL is correct and accessible
  • Check that your n8n instance is running
  • Ensure there are no firewall issues blocking the connection

MCP Server Not Showing

  • Restart Claude Desktop after configuration changes
  • Check the Claude Desktop logs for errors
  • Verify the path to index.js is absolute and correct

License

MIT

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选