MCPgee
MCPgee
MCPgeeMCPgee

Gcore

v1.0.0•Cloud Services•stable

Gcore official MCP server

gcoremcpai-integration
Share:
12
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Gcore?

Gcore is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to gcore official mcp server

Gcore official MCP server

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

Features

  • Gcore official MCP server

Use Cases

Manage Gcore cloud infrastructure through MCP.
Automate CDN and hosting operations with AI commands.
G-Core

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 1, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx gcore

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 Gcore

The Gcore MCP Server is the official Python-based MCP integration for Gcore's cloud platform, exposing tools to manage virtual machines, bare metal servers, GPU clusters, CDN, networking, storage, WAAP security, AI inference services, and billing through natural language AI assistants. It uses a flexible GCORE_TOOLS environment variable to select which tool groups are loaded — from narrow per-task subsets for most LLM clients to all tools at once for Claude Code (which uses deferred schema loading). Teams managing Gcore infrastructure use it to provision resources, inspect costs, and automate operations through conversational AI without switching to the web console.

Prerequisites

  • Python 3.10+ and uv (pip install uv) installed, OR uv alone for one-off execution via uvx
  • A Gcore account with a permanent API token (GCORE_API_KEY) — see Gcore docs on creating permanent API tokens
  • An MCP-compatible client: Claude Code, Cursor, Claude Desktop, or any MCP host
  • Optional: GCORE_CLOUD_PROJECT_ID and GCORE_CLOUD_REGION_ID if working with a specific project or region
1

Obtain a Gcore API key

Log in to the Gcore portal, navigate to Account Settings → API Tokens, and create a permanent API token. Copy it for use as GCORE_API_KEY.

2

Run the server without installing (uvx — recommended for quick start)

Use uvx to run the latest version of the server in a temporary environment with no persistent installation. Set GCORE_API_KEY and GCORE_TOOLS before running.

export GCORE_API_KEY="your_gcore_api_key"
export GCORE_TOOLS="instances,management"
uvx --from "gcore-mcp-server@git+https://github.com/G-Core/gcore-mcp-server.git" gcore-mcp-server
3

Configure Cursor IDE

Add the server to ~/.cursor/mcp.json. Use a narrowly-scoped GCORE_TOOLS value to avoid overwhelming the model context.

{
  "mcpServers": {
    "gcore-mcp-server": {
      "command": "uvx",
      "args": ["--from", "gcore-mcp-server@git+https://github.com/G-Core/gcore-mcp-server.git", "gcore-mcp-server"],
      "env": {
        "GCORE_API_KEY": "your_gcore_api_key",
        "GCORE_TOOLS": "instances,management"
      }
    }
  }
}
4

Configure Claude Code

Add the server to ~/.claude.json. Claude Code supports deferred tool loading, so you can safely set GCORE_TOOLS=* to load all tools without bloating the context window.

{
  "mcpServers": {
    "gcore-mcp-server": {
      "command": "uvx",
      "args": ["--from", "gcore-mcp-server@git+https://github.com/G-Core/gcore-mcp-server.git", "gcore-mcp-server"],
      "env": {
        "GCORE_API_KEY": "your_gcore_api_key",
        "GCORE_TOOLS": "*"
      }
    }
  }
}
5

Scope tools to your use case

Set GCORE_TOOLS to only the toolsets you need. Available predefined toolsets include: management, instances, baremetal, gpu_baremetal, gpu_virtual, networking, security, storage, ai, ai_ml, billing, containers, cleanup, list.

# For GPU cluster management only
export GCORE_TOOLS="gpu_baremetal,management"

# For full cloud operations
export GCORE_TOOLS="management,instances,storage,networking,security"

Gcore Examples

Client configuration (Cursor, scoped tools)

Cursor MCP config with instance and management tools loaded — suitable for VM lifecycle operations.

{
  "mcpServers": {
    "gcore-mcp-server": {
      "command": "uvx",
      "args": ["--from", "gcore-mcp-server@git+https://github.com/G-Core/gcore-mcp-server.git", "gcore-mcp-server"],
      "env": {
        "GCORE_API_KEY": "your_gcore_api_key",
        "GCORE_TOOLS": "instances,management",
        "GCORE_CLOUD_PROJECT_ID": "1",
        "GCORE_CLOUD_REGION_ID": "76"
      }
    }
  }
}

Prompts to try

Example prompts for common Gcore infrastructure operations.

- "List all virtual machine instances in my Gcore project"
- "Create a new VM instance with 4 vCPUs and 8GB RAM in the Amsterdam region"
- "Show me the current billing report and estimated monthly costs"
- "List all GPU bare metal clusters and their status"
- "Create a new security group that allows inbound HTTP and HTTPS traffic"

Troubleshooting Gcore

Authentication error: 401 Unauthorized

Verify GCORE_API_KEY is set to a valid permanent API token from the Gcore portal. Temporary session tokens are not supported. Regenerate the token if it may have expired.

Too many tools — AI model is confused or context is full

Narrow the GCORE_TOOLS value to only the toolsets relevant to your task, e.g. 'instances' or 'networking'. Avoid using GCORE_TOOLS=* in clients that don't support deferred schema loading (use it only with Claude Code).

uvx command not found

Install uv first: curl -LsSf https://astral.sh/uv/install.sh | sh (macOS/Linux) or the PowerShell equivalent on Windows. Then verify with 'uv --version' and ensure uv's bin directory is in your PATH.

Frequently Asked Questions about Gcore

What is Gcore?

Gcore is a Model Context Protocol (MCP) server that gcore official mcp server It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Gcore?

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

Which AI clients work with Gcore?

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

Is Gcore free to use?

Yes, Gcore is open source and available under the Apache-2.0 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

Gcore Alternatives — Similar Cloud Services Servers

Looking for alternatives to Gcore? 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": { "gcore": { "command": "npx", "args": ["-y", "gcore"] } } }

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

Read the full setup guide →

Ready to use Gcore?

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