N8N2MCP
Convert N8N agent / workflow into MCP servers, you can use it in Claude / Cursor / Super Chain
claude mcp add --transport stdio super-chain-n8n2mcp python main.py \ --env MCP_HOST="0.0.0.0" \ --env MCP_PORT="6545" \ --env N8N_AUTH="" \ --env FLASK_HOST="0.0.0.0" \ --env FLASK_PORT="5000" \ --env N8N_BASE_URL="https://your-n8n-instance.com" \ --env N8N_PASSWORD="your_n8n_password" \ --env N8N_USERNAME="your_n8n_username" \ --env SUPABASE_KEY="your_supabase_anon_key" \ --env SUPABASE_URL="https://your-project-id.supabase.co" \ --env X_N8N_API_KEY="your_n8n_api_key" \ --env N8N_BROWSER_ID="" \ --env N8N_BUILDER_URL="http://localhost:6545" \ --env SUPABASE_SERVICE_KEY="your_supabase_service_role_key"
How to use
N8N2MCP turns N8N workflows into MCP servers that can be invoked by AI assistants and MCP-compatible platforms. Once deployed, each MCP server exposes endpoints that allow you to list and call the converted MCP servers derived from your N8N workflows. Use the provided MCP URL in tools like Claude, Cursor, Super Chain, or any assistant that supports MCP routing. The integration workflow includes parsing N8N templates or uploading custom workflows, configuring credentials, and deploying the resulting MCP server so that AI agents can invoke your automations as function-like tools.
How to install
Prerequisites:
- Python 3.11+ (recommended)
- N8N instance (cloud or self-hosted)
- Supabase account for data storage
- Playwright (required for N8N authentication)
- Docker optional for containerized deployment
Quick Start (Docker Compose):
-
Clone the repository and install dependencies git clone https://github.com/Super-Chain/N8N2MCP.git cd N8N2MCP
-
Configure environment cp env.example .env
Edit .env with your actual values
-
Start with Docker Compose docker-compose up -d
Access: Flask App (Agent Marketplace) at http://localhost:5000
MCP Router at http://localhost:6545
-
View logs docker-compose logs -f
Manual Installation (Python):
-
Clone the repository git clone https://github.com/Super-Chain/N8N2MCP.git cd N8N2MCP
-
Install Python dependencies pip install -r requirements.txt
-
Install Playwright browsers (required for N8N authentication) playwright install
-
Configure environment cp .env.example .env
Edit .env as needed
-
Run the servers python main.py
Access: UI at http://localhost:5000 and MCP Router at http://localhost:6545
Additional notes
Notes:
- The system relies on a .env configuration. Ensure you populate SUPABASE_* and N8N_* values correctly for seamless operation.
- Playwright is required for N8N workflow execution; without proper installation, credentials may be dummy and functionality will be limited.
- If using Docker, ensure you have Docker and Docker Compose installed and that ports 5000 and 6545 are free.
- The MCP endpoints follow the pattern http://<host>:6545/mcp/<workflow_id>/<api_key> for access; use list endpoint to enumerate registered MCP servers.
- This setup exposes two parallel services: a Flask-based Agent Marketplace and the MCP Router. Both start with the same command (python main.py) under the provided environment configuration.
Related MCP Servers
mesh
One secure endpoint for every MCP server. Deploy anywhere.
mcp-memory
🔥🖥️ MCP Memory is a MCP Server that gives MCP Clients (Cursor, Claude, Windsurf and more) the ability to remember information about users (preferences, behaviors) across conversations.
mcp -echart
基于 mcp-go 框架构建的 mcp 服务，它提供了一个能动态生成 ECharts 图表页面的工具。
justcall
JustCall's Official MCP Server
mcp-doc-forge
MCP server that provides doc forge capabilities
AI-web mode
一个基于 MCP (Model Context Protocol) 的智能对话助手Web应用，支持实时聊天、工具调用和对话历史管理。
