Coreshub MCP Server

Name: Coreshub MCP Server
Author: coreshub

@coreshub

Repository

About Coreshub MCP Server

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

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-coreshub": {
      "command": "uv",
      "args": [
        "run",
        "src/coreshub_mcp_server"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Coreshub MCP Server?

Coreshub MCP Server is a Model Context Protocol server that enables AI assistants to interact with the Jishi Computing (基石智算) cloud platform. It provides tools for managing EPFS file systems, container instances, distributed training jobs, inference services, and their logs. It is designed for developers using MCP-compatible clients such as Cherry Studio.

How to use Coreshub MCP Server?

Install via uvx coreshub-mcp-server or clone from GitHub and run with uv run coreshub-mcp-server. Configure environment variables QY_ACCESS_KEY_ID, QY_SECRET_ACCESS_KEY, and CORESHUB_USER_ID with your Jishi Computing credentials. In Cherry Studio, add an MCP server with stdio type and the appropriate command for your OS. For CLI usage, run uv run src/coreshub_mcp_server with optional flags like --debug.

Key features of Coreshub MCP Server

Query EPFS file systems and their billing info
Retrieve container instance details with filtering
Get SSH connection info for specific instances
List distributed training tasks with time ranges
Fetch detailed logs for distributed training jobs
Query inference services and their logs
Extensible architecture for custom tools and prompts

Use cases of Coreshub MCP Server

AI assistant that helps users manage cloud storage (EPFS) and billing
Automated container instance monitoring and SSH access retrieval
Debugging distributed training tasks by fetching logs
Tracking status and logs of inference services on Jishi Computing

FAQ from Coreshub MCP Server

What are the prerequisites to run Coreshub MCP Server?

Python and uv must be installed. For best tool calling, a model with 32B parameters or higher is recommended.

What environment variables are required?

You must set QY_ACCESS_KEY_ID, QY_SECRET_ACCESS_KEY, and CORESHUB_USER_ID with your Jishi Computing account credentials.

How do I install the server via Cherry Studio?

Add an MCP server with "type": "stdio", command uvx and args ["coreshub-mcp-server"] (or a GitHub source). Include the three environment variables in the env object.

Can I run the server locally without Cherry Studio?

Yes. Clone the repository, set the environment variables, and run uv run src/coreshub_mcp_server from the project root. Use the --debug flag for verbose output.

How do I add a custom tool or prompt?

Create a Python file in the plugins/ directory, implement a subclass of BaseTool or BasePrompt, and call the register() method. Follow the example provided in the development section.