MCP server

The Cloudfleet CLI includes a built-in Model Context Protocol (MCP) server that enables AI assistants like Claude, Cursor, and other MCP-compatible tools to interact with your Cloudfleet infrastructure. This integration allows you to query clusters, inspect Kubernetes resources, and view infrastructure information through natural language conversations. The MCP server operates in read-only mode and provides access to any namespace that your configured user or token has permissions to view.

Prerequisites

Before using the MCP server, ensure you have:

The Cloudfleet CLI version 0.6.30 or later installed and configured
At least one authentication profile configured (see CLI authentication)
An MCP-compatible AI assistant or IDE

You can verify your CLI version by running:

cloudfleet --version

Configuration

To enable the Cloudfleet MCP server in your AI assistant, add the following configuration to your MCP settings file.

Edit your Claude Desktop configuration file:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "cloudfleet": {
      "command": "cloudfleet",
      "args": ["mcp"]
    }
  }
}

Edit your Claude Code settings file at ~/.claude/settings.json:

{
  "mcpServers": {
    "cloudfleet": {
      "command": "cloudfleet",
      "args": ["mcp"]
    }
  }
}

Edit your Cursor MCP configuration file at ~/.cursor/mcp.json:

{
  "mcpServers": {
    "cloudfleet": {
      "command": "cloudfleet",
      "args": ["mcp"]
    }
  }
}

Edit your VS Code MCP configuration file at .vscode/mcp.json in your workspace:

{
  "servers": {
    "cloudfleet": {
      "command": "cloudfleet",
      "args": ["mcp"]
    }
  }
}

Edit your Windsurf MCP configuration file at ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "cloudfleet": {
      "command": "cloudfleet",
      "args": ["mcp"]
    }
  }
}

Edit your Gemini CLI settings file at ~/.gemini/settings.json:

{
  "mcpServers": {
    "cloudfleet": {
      "command": "cloudfleet",
      "args": ["mcp"]
    }
  }
}

For other MCP-compatible AI tools, refer to their respective documentation for instructions on configuring MCP servers. The server command and arguments remain the same:

Command: cloudfleet
Arguments: ["mcp"] or ["mcp", "--profile", "your-profile-name"]

Using a specific profile

If you have multiple CLI profiles configured for different organizations, you can specify which profile to use with the --profile flag:

{
  "mcpServers": {
    "cloudfleet": {
      "command": "cloudfleet",
      "args": ["mcp", "--profile", "organization-1"]
    }
  }
}

The --profile flag is optional. If not specified, the CLI uses the default profile.

Available tools

The MCP server exposes the following tools to AI assistants:

Tool	Description
`who_am_i`	Returns information about the authenticated user, including user ID, email, name, organization ID, and admin status
`clusters_list`	Lists all Kubernetes clusters in your Cloudfleet organization
`clusters_get`	Returns detailed information about a specific cluster by cluster ID
`clusters_query`	Queries the Kubernetes API of a cluster directly, allowing access to any valid Kubernetes API endpoint (e.g., `/api/v1/namespaces`, `/apis/apps/v1/deployments`)

Example usage

Here are some example prompts you can use with AI assistants after configuring the MCP server:

Cluster management

“List all my Cloudfleet clusters”
“What is the status of my production cluster?”
“Show me the Kubernetes version running on cluster xyz”

Kubernetes queries

“List all pods in the default namespace of my cluster”
“Show me the deployments in the production namespace”
“What nodes are currently running in my cluster?”
“Are there any pods in a failed state?”

Infrastructure overview

“Give me an overview of my Cloudfleet infrastructure”
“Which cloud providers are connected to my cluster?”
“Show me the resource usage across my clusters”

Multiple organizations

If you work with multiple Cloudfleet organizations, you can configure separate MCP server entries for each:

{
  "mcpServers": {
    "cloudfleet-org-1": {
      "command": "cloudfleet",
      "args": ["mcp", "--profile", "organization-1"]
    },
    "cloudfleet-org-2": {
      "command": "cloudfleet",
      "args": ["mcp", "--profile", "organization-2"]
    }
  }
}

This allows you to interact with different organizations by referencing the appropriate server in your conversations.

Security considerations

The MCP server operates in read-only mode and uses your configured CLI profile’s authentication token. It can access any cluster and namespace that your user or API token has permissions to view. No write operations are performed through the MCP server.

Previous
← Install Cloudfleet CLI