Installation
- Docker (Recommended)
- Local Development
- npm Package
The fastest way to get started with MCPHub is using Docker:Or mount your custom configuration:
Initial Setup
1. Access the Dashboard
Open your browser and navigate to:2. Login
Use the default credentials:- Username:
admin
- Password:
admin123
Change these default credentials immediately after first login for security.
3. Configure Your First MCP Server
- Click “Add Server” in the dashboard
- Enter server details:
- Name: A unique identifier (e.g.,
fetch
) - Command: The executable command (
uvx
) - Args: Command arguments (
["mcp-server-fetch"]
) - Environment: Any required environment variables
- Name: A unique identifier (e.g.,
Basic Usage
Connecting AI Clients
Once your servers are configured, connect your AI clients using MCPHub endpoints:- All Servers
- Specific Group
- Individual Server
- Smart Routing
Access all configured MCP servers:
http://localhost:3000/mcp
Example: Adding Popular MCP Servers
Here are some popular MCP servers you can add:Web Fetch Server
Web Fetch Server
Playwright Browser Automation
Playwright Browser Automation
Amap Maps (with API key)
Amap Maps (with API key)
Slack Integration
Slack Integration
Next Steps
Server Management
Learn advanced server configuration and management
Group Management
Organize servers into logical groups
Smart Routing
Set up AI-powered tool discovery
API Reference
Explore the complete API documentation
Troubleshooting
Server won't start
Server won't start
- Check if the MCP server command is accessible in your PATH - Verify environment variables are correctly set - Check MCPHub logs for detailed error messages
Can't connect from AI client
Can't connect from AI client
- Ensure MCPHub is running on the correct port - Check firewall settings - Verify the endpoint URL format
Authentication issues
Authentication issues
- Verify credentials are correct - Check if JWT token is valid - Try clearing browser cache and cookies