N8N UVX
Self-hosted N8N integration for MCP UVX servers via Docker—run UVX-powered MCP servers locally in your N8N workflows without any cloud dependency.
What is N8N UVX?
N8N UVX is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to self-hosted n8n integration for mcp uvx servers via docker—run uvx-powered mcp servers locally in your n8n workflows without any cloud dependency.
Self-hosted N8N integration for MCP UVX servers via Docker—run UVX-powered MCP servers locally in your N8N workflows without any cloud dependency.
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Self-hosted N8N integration for MCP UVX servers via Docker—r
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx n8n-uvxConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use N8N UVX
n8n-uvx is a self-hosted Docker image that bundles N8N with the uv and uvx CLI tools (from Astral), enabling N8N workflows to spin up and call any UVX-powered MCP server locally without cloud dependencies. The image pre-installs system-level dependencies (curl, git, Chromium, build tools) alongside uv so that MCP servers written in Python can be launched directly from N8N's Execute Command or MCP Client nodes.
Prerequisites
- Docker 20.10 or higher installed
- Docker Compose installed
- Basic familiarity with N8N workflow editor
- Git installed to clone the repository
- A free port (default 5678) available on the host
Clone the repository
Clone the n8n-uvx repository to your local machine. The repo contains the Dockerfile, docker-compose.yml, and a .env.example file.
git clone https://github.com/The-AI-Workshops/n8n-uvx.git
cd n8n-uvxCreate the environment file
Copy the provided example environment file and edit the values to set your N8N admin credentials and data directory paths.
cp .env.example .env
# Edit .env with your preferred editorConfigure environment variables
The .env file controls N8N authentication, port, and data directories. Adjust the values before building the image.
N8N_BASIC_AUTH_ACTIVE=true
N8N_BASIC_AUTH_USER=admin
N8N_BASIC_AUTH_PASSWORD=your_secure_password
N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE=true
N8N_PORT=5678
N8N_DATA_DIR=./data
MCP_DATA_DIR=./mcpBuild the Docker image
Build the custom image that layers uv/uvx on top of the official N8N base image. This step installs all system dependencies and may take several minutes.
docker build -t n8n-uvx .Start the services
Use Docker Compose to start N8N in the background. The compose file mounts the data and mcp directories as named volumes for persistence.
docker-compose up -dAccess N8N and install the MCP Client node
Open N8N in your browser, sign in with the credentials set in .env, then install the community MCP Client node package from the N8N community nodes marketplace. You can then use 'Execute Command' nodes to call uvx MCP servers.
# Access N8N at:
http://localhost:5678N8N UVX Examples
Client configuration
Example docker-compose environment block showing all required variables.
{
"services": {
"n8n": {
"image": "n8n-uvx",
"environment": {
"N8N_BASIC_AUTH_ACTIVE": "true",
"N8N_BASIC_AUTH_USER": "admin",
"N8N_BASIC_AUTH_PASSWORD": "admin123",
"N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE": "true",
"N8N_PORT": "5678"
},
"ports": ["5678:5678"],
"volumes": ["./data:/home/node/.n8n", "./mcp:/mcp"]
}
}
}Prompts to try
How to use uvx MCP servers from inside N8N workflows.
- "In an Execute Command node, run: uvx mcp-server-fetch to launch a fetch MCP server"
- "Create an N8N workflow that calls a local Python MCP server via uvx on each webhook trigger"
- "Use the MCP Client node to connect to a uvx-managed server and list available tools"Troubleshooting N8N UVX
Docker build fails with missing dependencies
Ensure Docker has internet access during the build. If behind a corporate proxy, set HTTP_PROXY and HTTPS_PROXY build args: docker build --build-arg HTTP_PROXY=http://proxy:port -t n8n-uvx .
N8N does not start or crashes immediately
Run 'docker-compose logs n8n' to see the error output. Common causes are port 5678 already in use (change N8N_PORT in .env) or the data directory not being writable by the container user.
uvx command not found inside N8N Execute Command node
Confirm the image was built successfully with 'docker run --rm n8n-uvx uvx --version'. If the build used a cached layer, run 'docker build --no-cache -t n8n-uvx .' to rebuild from scratch.
Frequently Asked Questions about N8N UVX
What is N8N UVX?
N8N UVX is a Model Context Protocol (MCP) server that self-hosted n8n integration for mcp uvx servers via docker—run uvx-powered mcp servers locally in your n8n workflows without any cloud dependency. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install N8N UVX?
Follow the installation instructions on the N8N UVX GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with N8N UVX?
N8N UVX works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is N8N UVX free to use?
Yes, N8N UVX is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
N8N UVX Alternatives — Similar Business Applications Servers
Looking for alternatives to N8N UVX? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up N8N UVX in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use N8N UVX?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.