MCPgee
MCPgee
MCPgeeMCPgee

Coreshub

v1.0.0•Cloud Services•stable

mcp server for coreshub: https://coreshub.cn/

coreshubmcpai-integration
Share:
10
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Coreshub?

Coreshub is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for coreshub: https://coreshub.cn/

mcp server for coreshub: https://coreshub.cn/

This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • mcp server for coreshub: https://coreshub.cn/

Use Cases

Access CoreHub service
coreshub

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMar 4, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx coreshub

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Coreshub

The Coreshub MCP Server connects AI assistants to the 基石智算 (Coreshub) GPU cloud platform at coreshub.cn, exposing 8 tools that let you query EPFS file systems, billing info, container instances, SSH connection details, distributed training jobs and their logs, and inference services—all without leaving your chat interface.

Prerequisites

  • A Coreshub account at coreshub.cn with API credentials
  • QY_ACCESS_KEY_ID and QY_SECRET_ACCESS_KEY from the Coreshub console
  • CORESHUB_USER_ID (your account ID from the Coreshub dashboard)
  • Python 3.10+ and the uv package manager installed
  • Claude Desktop or another MCP-compatible client
1

Install uv (if not already installed)

Coreshub MCP Server is distributed via PyPI and works best with the uv package manager. Install it using the official installer script.

curl -LsSf https://astral.sh/uv/install.sh | sh
2

Install the Coreshub MCP Server

Use uvx to install and run the server directly from PyPI. No virtual environment setup is needed.

uvx coreshub-mcp-server
3

Set required environment variables

Obtain your Access Key ID, Secret Access Key, and User ID from the Coreshub console. Export them in your shell or add them to your MCP client configuration.

export QY_ACCESS_KEY_ID="your-access-key-id"
export QY_SECRET_ACCESS_KEY="your-secret-access-key"
export CORESHUB_USER_ID="your-user-id"
4

Add the server to Claude Desktop configuration

Edit your Claude Desktop config file to register the Coreshub MCP Server with the required credentials. On macOS the file is at ~/Library/Application Support/Claude/claude_desktop_config.json.

{
  "mcpServers": {
    "coreshub": {
      "command": "uvx",
      "args": ["coreshub-mcp-server"],
      "env": {
        "QY_ACCESS_KEY_ID": "your-access-key-id",
        "QY_SECRET_ACCESS_KEY": "your-secret-access-key",
        "CORESHUB_USER_ID": "your-user-id"
      }
    }
  }
}
5

Restart Claude Desktop and verify connection

Quit and reopen Claude Desktop. The Coreshub tools should now appear. You can also run the server with --list-plugins to confirm all 8 tools loaded correctly.

uvx coreshub-mcp-server --list-plugins

Coreshub Examples

Client configuration

Complete Claude Desktop config entry using uvx with environment credentials inline.

{
  "mcpServers": {
    "coreshub": {
      "command": "uvx",
      "args": ["coreshub-mcp-server"],
      "env": {
        "QY_ACCESS_KEY_ID": "AKID_XXXXXXXXXXXX",
        "QY_SECRET_ACCESS_KEY": "XXXXXXXXXXXXXXXXXXXX",
        "CORESHUB_USER_ID": "12345678"
      }
    }
  }
}

Prompts to try

Example prompts to use once the server is connected in Claude Desktop.

- "List all my EPFS file systems on Coreshub"
- "Show me the container instances running in zone xb3"
- "Get the SSH connection details for instance uuid abc-123"
- "Fetch the last 100 lines of logs for my inference service"
- "List all distributed training tasks from the past 7 days"

Troubleshooting Coreshub

Server starts but tools return authentication errors

Double-check that QY_ACCESS_KEY_ID, QY_SECRET_ACCESS_KEY, and CORESHUB_USER_ID are all set correctly and match exactly what is shown in the Coreshub console. Note that the key and secret are different values—do not swap them.

uvx command not found after installation

Ensure the uv binary directory is on your PATH. Run `source ~/.bashrc` or `source ~/.zshrc` after installing uv, or restart your terminal session before retrying.

Tools return empty results for containers or training tasks

Verify the correct zone is specified (xb3, xb2, or hb2). Some tools accept a zone parameter; if it defaults to an empty value, results will be empty. Explicitly pass the zone name in your prompt or check the server's context defaults.

Frequently Asked Questions about Coreshub

What is Coreshub?

Coreshub is a Model Context Protocol (MCP) server that mcp server for coreshub: https://coreshub.cn/ It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Coreshub?

Follow the installation instructions on the Coreshub GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Coreshub?

Coreshub works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Coreshub free to use?

Yes, Coreshub is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Coreshub Alternatives — Similar Cloud Services Servers

Looking for alternatives to Coreshub? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.

Open WebUI

★ 138.2k

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Anything LLM

★ 60.4k

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

LocalAI

★ 46.4k

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Nacos

★ 33.0k

an easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.

Xiaozhi ESP32

★ 26.7k

本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.

Gateway

★ 11.8k

A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Browse More Cloud Services MCP Servers

Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Cloud ServicesBrowse All Servers

Quick Config Preview

{ "mcpServers": { "coreshub": { "command": "npx", "args": ["-y", "coreshub"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Coreshub?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides