kb-cloud

The KubeBlocks Cloud MCP Server exposes a set of MCP tools that let AI assistants interact with your KubeBlocks Cloud resources in a standardized, tool-calling manner. It provides access to organizations, environments, instances, and backups through a secure API layer. To enable usage in editors like VS Code, you configure inputs for your API credentials and run the server container, which then responds to MCP tool calls such as list_organizations, get_organization, list_environments, get_environment, list_instances, get_instance, list_backups, and get_backup. You can start it using the provided Docker image, passing your API credentials as environment variables. You can also adjust server behavior with optional site URL and debug/export settings. The server is designed to work with the MCP protocol: you send structured tool calls, and it returns results in a predictable format suitable for downstream assistants and automation.

Prerequisites:

• Docker installed and running (for the recommended deployment method)
• Optionally, Go 1.20+ if you prefer building from source (as described in the project README)

Recommended installation (Docker):

1. Ensure you have your KubeBlocks Cloud API credentials (API key name and secret).
2. Pull and run the MCP server container with your credentials:

# Example run (replace placeholders with real values or set via environment variables)
docker run -i --rm \
  -e KB_CLOUD_API_KEY_NAME=your-api-key-name \
  -e KB_CLOUD_API_KEY_SECRET=your-api-key-secret \
  apecloud/kb-cloud-mcp-server:latest

If you prefer building from source:

1. Clone the repository:

git clone https://github.com/apecloud/kb-cloud-mcp-server.git
cd kb-cloud-mcp-server

2. Install dependencies and build (Go 1.20+ required):

go mod tidy
go build -o kb-cloud-mcp-server ./cmd/server

3. Run the built binary:

./kb-cloud-mcp-server

Configuration via VS Code (optional):

• You can add an MCP configuration block to VS Code's user settings or a workspace file to drive tool calls. The example in the README demonstrates wiring the docker-based server with prompts for API credentials.

Tips and notes:

• Ensure KB_CLOUD_API_KEY_NAME and KB_CLOUD_API_KEY_SECRET are kept secure and not exposed in logs.
• You can set KB_CLOUD_SITE to point to a custom KubeBlocks Cloud API endpoint if needed.
• You can adjust logging and translation behavior using KB_CLOUD_MCP_LOG_LEVEL, KB_CLOUD_MCP_EXPORT_TRANSLATIONS, and KB_CLOUD_DEBUG.
• When using the Docker approach, remember to provide environment variables that map to your credentials for the container to authenticate properly.
• If you run into network or authentication errors, verify that the API credentials are valid and have the required permissions to access Organizations, Environments, Instances, and Backups.
• The server supports internationalization via translation helpers; you can enable or export translations as needed.