KubeBlocks Cloud

Provides an MCP-based API to manage KubeBlocks Cloud resources such as organizations, environments, instances, and backups via standardized tool calls.

GitHub Stars

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "apecloud-kb-cloud-mcp-server": {
      "command": "./kb-cloud-mcp-server",
      "args": [
        "stdio",
        "--api-key=your-api-key-name",
        "--api-secret=your-api-key-secret"
      ],
      "env": {
        "KB_CLOUD_API_KEY_NAME": "YOUR_API_KEY_NAME",
        "KB_CLOUD_API_KEY_SECRET": "YOUR_API_KEY_SECRET"
      }
    }
  }
}

The KubeBlocks Cloud MCP Server provides a Model Context Protocol interface to manage and query KubeBlocks Cloud resources. It enables AI assistants to securely interact with organizations, environments, instances, and backups through a standardized tool-calling interface.

How to use

When you connect a client to the MCP server, you can list and fetch details for KubeBlocks Cloud resources such as organizations, environments, instances, and backups. Use the available MCP tools to automate resource management, retrieve data, and build AI-powered workflows that provision and manage cloud resources.

How to install

Prerequisites: you need Go 1.20+ installed on your system.

Install and run the MCP server from source using the following steps.

# Clone the MCP server repository
git clone https://github.com/apecloud/kb-cloud-mcp-server.git
cd kb-cloud-mcp-server

# Resolve dependencies and build
go mod tidy
go build -o kb-cloud-mcp-server ./cmd/server

Configuration and usage notes

Environment variables you can set to control the server behavior include API credentials and logging details.

API credentials and endpoint (examples shown here as placeholders):

export KB_CLOUD_API_KEY_NAME=your-api-key-name
export KB_CLOUD_API_KEY_SECRET=your-api-key-secret
export KB_CLOUD_SITE=https://api.apecloud.com
export KB_CLOUD_MCP_LOG_LEVEL=info
export KB_CLOUD_MCP_EXPORT_TRANSLATIONS=true
export KB_CLOUD_DEBUG=false

Start the server using a local binary

Run the compiled binary directly in stdio mode to start serving MCP requests.

./kb-cloud-mcp-server stdio --api-key=your-api-key-name --api-secret=your-api-key-secret

Start the server using Docker (stdio configuration)

You can run the MCP server in a Docker container as a stdio server. This approach passes API credentials as environment variables to the container.

"command": "docker",
"args": [
  "run",
  "-i",
  "--rm",
  "-e",
  "KB_CLOUD_API_KEY_NAME",
  "-e",
  "KB_CLOUD_API_KEY_SECRET",
  "apecloud/kb-cloud-mcp-server:latest"
]

Configuration file

You can also provide a configuration file to set server options.

# .kb-cloud-mcp-server.yaml
log_level: info
api_key: your-api-key-name
api_secret: your-api-key-secret
site_url: https://api.apecloud.com

Notes

The server supports exporting translations and has a debug mode for the API client. Use these features to aid integration and troubleshooting.

Available tools

list_organizations

List all organizations you have access to; no parameters required.

get_organization

Get details of a specific organization using its organizationId.

list_environments

List all environments within a given organization using organizationId.

get_environment

Get details of a specific environment using organizationId and environmentId.

list_instances

List all instances within a specific environment using organizationId and environmentId.

get_instance

Get details of a specific instance using organizationId, environmentId, and instanceId.

list_backups

List all backups for a specific instance using organizationId, environmentId, and instanceId.

get_backup

Get details of a specific backup using organizationId, environmentId, environmentId, instanceId, and backupId.

Built by

VeilStrat

AI signals for GTM teams