MCP Hub
An AI-native management hub that enables users to control WordPress, WooCommerce, and various self-hosted services like Gitea and Supabase through AI assistants. It provides a comprehensive suite of nearly 600 tools for managing content, ecommerce st
What is MCP Hub?
MCP Hub is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ai-native management hub that enables users to control wordpress, woocommerce, and various self-hosted services like gitea and supabase through ai assistants. it provides a comprehensive suite of near...
An AI-native management hub that enables users to control WordPress, WooCommerce, and various self-hosted services like Gitea and Supabase through AI assistants. It provides a comprehensive suite of nearly 600 tools for managing content, ecommerce st
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- list-all-tools
- call-tool
- find-tools
- get-tool
- list-all-tools-in-server
Use Cases
Maintainer
Works with
Installation
NPM
npx -y mcp-hub-mcpManual Installation
npx -y mcp-hub-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Hub
MCP Hub is a self-hosted, extensible MCP server framework that lets you expose reusable development conventions, prompts, and tooling to AI assistants over a Streamable HTTP transport. It is built with FastMCP and organizes capabilities into domain-specific modules (e.g. Python/uv conventions), making it easy to share consistent engineering standards across your team's AI-powered workflows. Developers use it to run a persistent MCP endpoint on their own infrastructure and connect Claude, Cursor, or any MCP-compatible client without relying on third-party services.
Prerequisites
- Python 3.10+ and uv package manager installed
- Node.js 18+ (if using npx launch variant)
- An MCP-compatible client such as Claude Desktop, Cursor, or VS Code with MCP support
- Basic familiarity with running a local server process
Clone the repository
Clone the mcp-hub repository to your local machine so you can configure and run it as a self-hosted server.
git clone https://github.com/shanezchang/mcp-hub.git
cd mcp-hubCreate your environment file
Copy the provided example environment file and adjust the host and port values if you need to bind to a different address or port. By default the server listens on 0.0.0.0:9001.
cp .env.example .env
# Edit .env to set MCP_HOST and MCP_PORT if neededInstall dependencies
Use uv to install the Python dependencies declared in the project. This sets up FastMCP and any other required packages.
uv syncStart the MCP server
Run the server using uv. It will bind to the configured host and port and expose all registered prompts and tools over the Streamable HTTP transport.
uv run main.pyList available tools and prompts
Verify what capabilities the server is exposing by listing registered tools and prompts. This is useful after adding new modules.
uv run fastmcp list main.py
uv run fastmcp list main.py --promptsConnect your MCP client
Point your MCP-compatible client at the running server using the Streamable HTTP transport. Replace localhost with your server's IP if running remotely.
MCP Hub Examples
Client configuration
Configure Claude Desktop or another MCP client to connect to your self-hosted mcp-hub instance over HTTP.
{
"mcpServers": {
"mcp-hub": {
"command": "npx",
"args": ["-y", "mcp-hub-mcp"],
"env": {
"MCP_HOST": "0.0.0.0",
"MCP_PORT": "9001"
}
}
}
}Prompts to try
Once connected, use these prompts to interact with the server's registered capabilities.
- "What Python/uv conventions should I follow for this project?"
- "List all available tools on this MCP server"
- "Show me the dev_python_uv prompt details"Troubleshooting MCP Hub
Server fails to start with 'address already in use' error
Change MCP_PORT in your .env file to an unused port (e.g. 9002) and restart the server with `uv run main.py`.
MCP client cannot connect to the server
Ensure the server is running and that your firewall allows traffic on the configured port. If running Docker or a VM, verify port forwarding is set up correctly.
No tools or prompts appear in the client
Run `uv run fastmcp list main.py` to confirm the server is registering capabilities. Check that your modules directory contains valid FastMCP-decorated functions.
Frequently Asked Questions about MCP Hub
What is MCP Hub?
MCP Hub is a Model Context Protocol (MCP) server that ai-native management hub that enables users to control wordpress, woocommerce, and various self-hosted services like gitea and supabase through ai assistants. it provides a comprehensive suite of nearly 600 tools for managing content, ecommerce st It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Hub?
Install via npm with the command: npx -y mcp-hub-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with MCP Hub?
MCP Hub works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Hub free to use?
Yes, MCP Hub is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
MCP Hub Alternatives — Similar Business Applications Servers
Looking for alternatives to MCP Hub? 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 MCP Hub 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 MCP Hub?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.