MCP Hub
A hub server that connects to and manages other MCP servers.
MCP-Hub-MCP Server
A hub server that connects to and manages other MCP (Model Context Protocol) servers.
Overview
This project builds an MCP hub server that connects to and manages multiple MCP (Model Context Protocol) servers through a single interface. It helps prevent excessive context usage and pollution from infrequently used MCPs (e.g., Atlassian MCP, Playwright MCP) by allowing you to connect them only when needed. This reduces AI mistakes and improves performance by keeping the active tool set focused and manageable.
Key Features
- Automatic connection to other MCP servers via configuration file
- List available tools on connected servers
- Call tools on connected servers and return results
Configuration
Add this to your mcp.json:
Using npx
{
"mcpServers": {
"other-tools": {
"command": "npx",
"args": [
"-y",
"mcp-hub-mcp",
"--config-path",
"/Users/username/mcp.json"
]
}
}
}
Installation and Running
Requirements
- Node.js 18.0.0 or higher
- npm, yarn, or pnpm
Installation
# Clone repository
git clone <repository-url>
cd mcp-hub-mcp
# Install dependencies
npm install
# or
yarn install
# or
pnpm install
Build
npm run build
# or
yarn build
# or
pnpm build
Run
npm start
# or
yarn start
# or
pnpm start
Development Mode
npm run dev
# or
yarn dev
# or
pnpm dev
Configuration File
The MCP-Hub-MCP server uses a Claude Desktop format configuration file to automatically connect to other MCP servers. You can specify the configuration file in the following ways:
- Environment variable: Set the
MCP_CONFIG_PATHenvironment variable to the configuration file path - Command line argument: Use the
--config-pathoption to specify the configuration file path - Default path: Use
mcp-config.jsonfile in the current directory
Configuration file format:
{
"mcpServers": {
"serverName1": {
"command": "command",
"args": ["arg1", "arg2", ...],
"env": { "ENV_VAR1": "value1", ... }
},
"serverName2": {
"command": "anotherCommand",
"args": ["arg1", "arg2", ...]
}
}
}
Example:
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/Users/username/Desktop",
"/Users/username/Downloads"
]
},
"other-server": {
"command": "node",
"args": ["path/to/other-mcp-server.js"]
}
}
}
Usage
The MCP-Hub-MCP server provides the following tools:
1. list-all-tools
Returns a list of tools from all connected servers.
{
"name": "list-all-tools",
"arguments": {}
}
2. call-tool
Calls a tool on a specific server.
serverName: Name of the MCP server to call the tool fromtoolName: Name of the tool to calltoolArgs: Arguments to pass to the tool
{
"name": "call-tool",
"arguments": {
"serverName": "filesystem",
"toolName": "readFile",
"toolArgs": {
"path": "/Users/username/Desktop/example.txt"
}
}
}
3. find-tools
Find tools matching a regex pattern across all connected servers (grep-like functionality).
pattern: Regex pattern to search for in tool names and descriptionssearchIn: Where to search: "name", "description", or "both" (default: "both")caseSensitive: Whether the search should be case-sensitive (default: false)
{
"name": "find-tools",
"arguments": {
"pattern": "file",
"searchIn": "both",
"caseSensitive": false
}
}
Example patterns:
"file"- Find all tools containing "file""^read"- Find all tools starting with "read""(read|write).*file"- Find tools for reading or writing files"config$"- Find tools ending with "config"
Example output:
{
"filesystem": [
{
"name": "readFile",
"description": "Read the contents of a file",
"inputSchema": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Path to the file to read"
}
},
"required": ["path"]
}
},
{
"name": "writeFile",
"description": "Write content to a file",
"inputSchema": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Path to the file to write"
},
"content": {
"type": "string",
"description": "Content to write to the file"
}
},
"required": ["path", "content"]
}
}
]
}
Commit Message Convention
This project follows Conventional Commits for automatic versioning and CHANGELOG generation.
Format: <type>(<scope>): <description>
Examples:
feat: add new hub connection featurefix: resolve issue with server timeoutdocs: update API documentationchore: update dependencies
Types:
feat: New feature (MINOR version bump)fix: Bug fix (PATCH version bump)docs: Documentation only changesstyle: Changes that do not affect the meaning of the coderefactor: Code change that neither fixes a bug nor adds a featureperf: Code change that improves performancetest: Adding missing tests or correcting existing testschore: Changes to the build process or auxiliary tools
Breaking Changes:
Add BREAKING CHANGE: in the commit footer to trigger a MAJOR version bump.
Other Links
License
MIT
संबंधित सर्वर
Kone.vc
प्रायोजकMonetize your AI agent with contextual product recommendations
MCP-Zentao
An API integration for the Zentao project management system, supporting task management and bug tracking.
physbound
PhysBound is a specialized "Physics Linter" for AI that deterministically validates RF and thermodynamic claims against hard physical limits, preventing hallucinations in engineering workflows.
SWOTPal — SWOT Analysis
Generate SWOT analyses, competitive comparisons, and browse 100+ pre-built industry examples for any company, brand, or topic. Supports 12 languages.
Paperless-MCP
An MCP server for interacting with a Paperless-NGX API server. This server provides tools for managing documents, tags, correspondents, and document types in your Paperless-NGX instance.
Rezdy Agent
Search marketplace products, manage bookings, and handle customer relationships using the Rezdy Agent API.
Autofill PDF
Autofill PDF is an MCP server that connects your Instafill.ai workspace to the Claude and ChatGPT MCP clients, allowing users to upload, search, and automatically fill PDF forms directly from chat.
Portfolio Manager MCP Server
A server providing tools and resources for managing and analyzing investment portfolios.
Great Question
Great Question is an Agentic UX research platform for product builders. Its MCP lets AI agents create studies directly from any AI tool, surface insights, find the right research candidates, and query your entire research repository.
QrVerloz MCP Server
Instantly generate QR codes without an account — active for 90 days, claimable forever, with destination retargeting and scan analytics.
go-review-mcp
Code reviewing following the Go style guides directly from official and recommended sources.