What is the purpose of MCP-Hub MCP?
It connects to multiple MCP servers, lists their tools, and executes them. It is created mainly to bypass Cursor’s 40-tool MCP limit and reduce AI errors.

@warpdev
Basic information
A hub server that connects to and manages other MCP (Model Context Protocol) servers.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-hub-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-hub-mcp",
"--config-path",
"/Users/username/mcp.json"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
MCP-Hub MCP is a hub server that connects to and manages other MCP (Model Context Protocol) servers, allowing users to list their tools and execute them. It is especially useful for bypassing Cursor’s 40-tool MCP limit and reducing AI mistakes by hiding infrequently used tools.
Install via npx with the mcp-hub-mcp package and specify a config path. Configure the hub by providing a JSON configuration file (Claude Desktop format) via environment variable (MCP_CONFIG_PATH), CLI argument (--config-path), or a default mcp-config.json. Once connected, use the tools list-all-tools and call-tool to interact with all managed servers.
It connects to multiple MCP servers, lists their tools, and executes them. It is created mainly to bypass Cursor’s 40-tool MCP limit and reduce AI errors.
Node.js 18.0.0 or higher, with npm, yarn, or pnpm.
Use a configuration file in Claude Desktop format via the `MCP_CONFIG_PATH` environment variable, the `--config-path` command line argument, or a default `mcp-config.json` file in the current directory.
Two tools: `list-all-tools` (returns all tools from connected servers) and `call-tool` (calls a tool on a specific server using `serverName`, `toolName`, and `toolArgs`).
The README does not mention authentication or custom transport support.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
不止于 CSS

Model Context Protocol Servers

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Comments