N8N Claw
OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templates, Expert Agents with delegated sub-agents, proactive task management, media understanding - self-hosted with one setup script
What is N8N Claw?
N8N Claw is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to openclaw-inspired autonomous ai agent built entirely in n8n. adaptive rag-powered memory, skills via mcp templates, expert agents with delegated sub-agents, proactive task management, media understand...
OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templates, Expert Agents with delegated sub-agents, proactive task management, media understanding - self-hosted with one setup script
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- OpenClaw-inspired autonomous AI agent built entirely in n8n.
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx n8n-clawConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use N8N Claw
N8N Claw is a self-hosted, autonomous AI agent built entirely inside n8n workflows, inspired by the OpenClaw architecture. It combines adaptive RAG-powered long-term memory (hybrid semantic + full-text + entity search), a knowledge graph that auto-tracks people and companies, task management with priorities, and a skills system backed by 43+ pre-built MCP templates. The agent is reachable via Telegram, Discord, Slack, or a webhook HTTP API, and can delegate subtasks to 100+ specialist Expert Agents. Developers and teams use it as a privacy-preserving, model-agnostic AI assistant that lives entirely on their own infrastructure.
Prerequisites
- A Linux VPS running Ubuntu 22.04/24.04 or Debian 13+ with at least 4 GB RAM and 15 GB free disk
- A domain name (or sslip.io will be used automatically for an IP-based HTTPS domain)
- A Telegram Bot Token from @BotFather and your Chat ID from @userinfobot
- An API key for at least one LLM provider (Anthropic, OpenAI, OpenRouter, DeepSeek, Gemini, Mistral, or an Ollama endpoint)
- Git installed on the server
Clone the repository
SSH into your VPS and clone the n8n-claw repository to get the setup script and workflow files.
git clone https://github.com/freddy-schuetz/n8n-claw.git && cd n8n-clawRun the interactive setup script
Execute the setup script. It will ask for your Telegram credentials, LLM provider, domain name, and optional integrations (Discord, Paperclip, embedding provider), then write a .env file and start all Docker services.
./setup.shAccess the n8n workflow editor
Once the script finishes, open your browser to the n8n interface and log in. All workflows are pre-imported and active.
# Open in browser:
# http://YOUR-IP:5678Verify the Telegram interface
Send your bot a message on Telegram. The agent should reply, confirming that the webhook and memory systems are online.
Install optional skills
Ask the agent to list available skills and install any you want (e.g., weather, web search, Google services).
Reconfigure or upgrade if needed
Use the --force flag to re-run the full setup, or the --upgrade-pg17 flag to migrate an existing install to PostgreSQL 17.
./setup.sh --force
# or
sudo ./setup.sh --upgrade-pg17N8N Claw Examples
Client configuration (webhook API)
Use the webhook endpoint to send messages programmatically. Replace YOUR-DOMAIN and YOUR_WEBHOOK_SECRET with the values from your .env file.
curl -X POST https://YOUR-DOMAIN/webhook/agent \
-H "Content-Type: application/json" \
-H "X-API-Key: YOUR_WEBHOOK_SECRET" \
-d '{"message": "What are my open tasks?", "user_id": "alice"}'Prompts to try
Send these via Telegram or the webhook API to explore the agent's capabilities.
- "Remember that I prefer morning meetings before 10am."
- "Remind me in 30 minutes to check the oven."
- "Create a task: prepare presentation for Friday, high priority."
- "Research the best hiking trails in Tyrol with sources."
- "What skills are available? Install weather-openmeteo."
- "Give me a daily briefing every morning at 8am."
- "Build me an MCP server for the OpenLibrary API."Troubleshooting N8N Claw
The setup script fails during Docker service startup
Ensure Docker and Docker Compose are installed and the user running the script is in the docker group. Run 'docker info' to confirm Docker is accessible, then re-run ./setup.sh.
Telegram messages are not triggering agent responses
Check that TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID in .env are correct. The webhook must be registered with Telegram — re-running ./setup.sh --force will re-register it. Also verify the domain resolves and has a valid TLS certificate.
LLM API calls fail or return errors
Confirm the correct API key is set in .env for the chosen LLM_PROVIDER and that the key has sufficient quota. You can change providers by editing LLM_PROVIDER and the corresponding key in .env, then restarting the n8n container.
Frequently Asked Questions about N8N Claw
What is N8N Claw?
N8N Claw is a Model Context Protocol (MCP) server that openclaw-inspired autonomous ai agent built entirely in n8n. adaptive rag-powered memory, skills via mcp templates, expert agents with delegated sub-agents, proactive task management, media understanding - self-hosted with one setup script It connects AI assistants to external tools and data sources through a standardized interface.
How do I install N8N Claw?
Follow the installation instructions on the N8N Claw GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with N8N Claw?
N8N Claw works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is N8N Claw free to use?
Yes, N8N Claw is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
N8N Claw Alternatives — Similar Business Applications Servers
Looking for alternatives to N8N Claw? 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 Claw 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 Claw?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.