</>MCP Agents Market
MCP Server

selfhost-ai

by kossakovsky926ShellUpdated 2026-09-09

🚀 Self-hosted AI automation platform. Deploy n8n, Ollama, Flowise, RAG, Supabase & 30+ tools with one command. Auto HTTPS. Free Zapier/Make alternative.

Claude CodeCursorWindsurfVS Code Copilot

selfhost-ai is a comprehensive Docker-based platform for deploying AI automation infrastructure with an integrated n8n-MCP server. The platform bundles over 30 tools including n8n workflow automation, Ollama for local LLMs, Flowise for AI agents, vector databases (Qdrant, Weaviate), and RAG engines, all configured behind Caddy reverse proxy with automatic HTTPS. The n8n-MCP component specifically gives AI coding assistants like Claude Code, Cursor, and Windsurf indexed access to every n8n node's documentation, property schemas, thousands of workflow templates, and the ability to create and update workflows directly from your IDE when connected with an API key.

Key Features

n8n-MCP server exposes n8n node documentation, schemas, and workflow templates to AI coding assistants via Model Context Protocol
Single-command installation deploys 30+ AI tools including n8n, Ollama, Flowise, Supabase, vector databases, and monitoring stack
Automatic HTTPS configuration with Caddy reverse proxy and Let's Encrypt certificates for all services
Scalable n8n deployment with queue mode, Redis task management, configurable workers and task runners for parallel processing
Optional import of 300+ community n8n workflows covering AI agents, chatbots, RAG, email automation, and social media
Built-in monitoring with Grafana and Prometheus including n8n-specific dashboards and workflow alert rules
Multi-GPU Ollama support with configurable instance count for parallel local LLM hosting
n8n Assistant sandbox with Docker-in-Docker isolation for code execution by n8n's AI Assistant and Agents preview

Use Cases

  • 01Enable AI coding assistants to browse n8n documentation and create workflows without leaving your IDE
  • 02Build self-hosted AI automation workflows combining local LLMs, vector databases, and 400+ n8n integrations
  • 03Deploy private ChatGPT alternative with Open WebUI connected to locally-hosted Ollama models
  • 04Create RAG applications using integrated vector stores (Qdrant, Weaviate) and document processing tools
  • 05Monitor workflow execution health with pre-configured Grafana dashboards and alert rules for failed/stalled workflows
  • 06Run multiple local LLMs simultaneously on multi-GPU servers with dedicated Ollama instances per model

Related MCP Servers

View more

markitdown

Python tool for converting files and office documents to Markdown.

MCP Server188k

firecrawl

The context API to search, scrape, and interact with the web at scale. 🔥

MCP Server187.9k

prompts.chat

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

MCP Server171.9k

langflow

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

MCP Server155.5k

selfhost-ai — FAQ

What is the n8n-MCP server included in selfhost-ai?+

n8n-MCP is a Model Context Protocol server that gives AI coding assistants indexed access to n8n node documentation, property schemas, and workflow templates. When configured with an n8n API key, it enables assistants to create and update workflows in your n8n instance directly from your IDE.

How do I install and access the n8n-MCP server?+

Run the installer with 'git clone https://github.com/kossakovsky/selfhost-ai && cd selfhost-ai && sudo bash ./scripts/install.sh', then select n8n-MCP in the service wizard. Access it at n8n-mcp.yourdomain.com/mcp using 'npx -y mcp-remote https://n8n-mcp.yourdomain.com/mcp --header "Authorization: Bearer <N8N_MCP_AUTH_TOKEN>"' with the token from your Welcome Page.

Which AI coding assistants work with n8n-MCP?+

The MCP server works with Claude Code, Cursor, Windsurf, and VS Code Copilot. Any MCP-compatible client can connect using the remote MCP protocol with bearer token authentication.

What are the prerequisites for running selfhost-ai?+

You need a VPS with Ubuntu 24.04 LTS, a registered domain with wildcard DNS A-record pointing to your server IP, minimum 4GB RAM/2 CPU/40GB disk for basic setup (20GB RAM/4 CPU/60GB disk for all services). Optional OpenAI API key can be provided for Supabase AI features and Crawl4ai.

Is selfhost-ai free and open source?+

Yes, selfhost-ai is completely free and licensed under Apache 2.0. All bundled tools are open-source, though some services may optionally integrate with commercial API providers like OpenAI or Anthropic.

How do I enable n8n-MCP to manage workflows in my n8n instance?+

Create an n8n API key under Settings → n8n API in your n8n instance, set N8N_API_KEY in .env, and run 'make restart'. Without an API key, n8n-MCP operates in documentation-only mode.

How do I install selfhost-ai?+

Open the source repository on GitHub and follow its README. selfhost-ai is a mcp server — MCP Agents Market links you directly to the official repo.

Is selfhost-ai free?+

selfhost-ai is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches

Developer Tools MCP ServersWorkflow MCP ServersCloud & DevOps MCP ServersBest SkillsBest PluginsBest AgentsTop rated listingsClaude Code toolsBrowse all categories