Skip to main content

AI-Powered Server Management - Connect Claude, Cursor, and other AI tools directly to your Alpacon infrastructure

Project description

Alpacon MCP Server

๐Ÿš€ AI-Powered Server Management - Connect Claude, Cursor, and other AI tools directly to your Alpacon infrastructure

An advanced MCP (Model Context Protocol) server that bridges AI assistants with Alpacon's server management platform, enabling natural language server administration, monitoring, and automation.

Python Version MCP Compatible License

โœจ What is Alpacon MCP Server?

The Alpacon MCP Server transforms how you interact with your server infrastructure by connecting AI assistants directly to Alpacon's management platform. Instead of switching between interfaces, you can now manage servers, monitor metrics, execute commands, and troubleshoot issues using natural language.

๐ŸŽฏ Key Benefits

  • Natural Language Server Management - "Show me CPU usage for all web servers in production"
  • AI-Powered Troubleshooting - "Investigate why server-web-01 is slow and suggest fixes"
  • Multi-Workspace Support - Connect to your Alpacon workspaces with secure API authentication
  • Real-Time Monitoring Integration - Access metrics, logs, and events through AI conversations
  • Secure Websh & File Operations - Execute commands and transfer files via AI interface

๐ŸŒŸ Core Features

๐Ÿ–ฅ๏ธ Server Management

  • List and monitor servers in your workspace
  • Get detailed system information and specifications
  • Create and manage server documentation
  • Multi-workspace support with API token management

๐Ÿ“Š Real-Time Monitoring

  • CPU, memory, disk, and network metrics
  • Performance trend analysis
  • Top server identification
  • Custom alert rule management
  • Comprehensive health dashboards

๐Ÿ’ป System Administration

  • User and group management
  • Package inventory and updates
  • Network interface monitoring
  • Disk and partition analysis
  • System time and uptime tracking

๐Ÿ”ง Remote Operations

  • Websh sessions for secure shell access
  • Command execution with real-time output
  • File upload/download via WebFTP
  • Session management and monitoring

๐Ÿ“‹ Event Management

  • Command acknowledgment and tracking
  • Event search and filtering
  • Execution history and status
  • Automated workflow coordination

๐Ÿš€ Quick Start

For First-Time Users (Recommended)

Just run this command and follow the interactive setup:

uvx alpacon-mcp

That's it! The setup wizard will:

  1. โœ… Ask for your region (default: ap1)
  2. โœ… Ask for your workspace name
  3. โœ… Ask for your API token
  4. โœ… Save configuration automatically
  5. โœ… Test the connection
  6. โœ… Show you the Claude Desktop config to copy

No manual file editing required!

Get Your API Token

Before running the setup, get your API token:

  1. Visit https://alpacon.io
  2. Log in to your account
  3. Click "API Token" in left sidebar
  4. Create new token or copy existing one
  5. Configure ACL permissions (important for command execution)
  6. Copy the token (starts with alpat-...)

Connect to Your MCP Client

After setup completes, add the configuration to your MCP client:

{
  "mcpServers": {
    "alpacon": {
      "command": "uvx",
      "args": ["alpacon-mcp"]
    }
  }
}

Client-specific locations:

  • Claude Desktop:
    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Cursor: .cursor/mcp.json in your project
  • VS Code: MCP extension settings

Restart or reconnect your MCP client and you're ready! ๐ŸŽ‰


๐Ÿ“‹ CLI Commands Reference

uvx alpacon-mcp                                # Start server (auto-setup if needed)
uvx alpacon-mcp setup                          # Run setup wizard (shows token file path)
uvx alpacon-mcp setup --local                  # Use project config instead of global
uvx alpacon-mcp setup --token-file ~/my.json   # Use custom file location
uvx alpacon-mcp test                           # Test your connection
uvx alpacon-mcp list                           # Show configured workspaces
uvx alpacon-mcp add                            # Add another workspace (shows path)

๐Ÿ”ง Advanced Installation Options

Option A: Install UV (if not already installed)

curl -LsSf https://astral.sh/uv/install.sh | sh

Option B: Manual Configuration

If you prefer to manually configure tokens:

Global Configuration (recommended):

mkdir -p ~/.alpacon-mcp
echo '{
  "ap1": {
    "production": "alpat-ABC123xyz789...",
    "staging": "alpat-DEF456uvw012..."
  }
}' > ~/.alpacon-mcp/token.json

Project-Local Configuration:

mkdir -p config
echo '{
  "ap1": {
    "my-workspace": "alpat-ABC123xyz789..."
  }
}' > config/token.json

Environment Variables:

export ALPACON_MCP_AP1_PRODUCTION_TOKEN="alpat-ABC123xyz789..."
uvx alpacon-mcp

Option C: Development Installation

git clone https://github.com/alpacax/alpacon-mcp.git
cd alpacon-mcp
uv venv && source .venv/bin/activate
uv install
python main.py

๐Ÿ”Œ Connect to Other AI Tools

Cursor IDE

Create .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "alpacon": {
      "command": "uvx",
      "args": ["alpacon-mcp"]
    }
  }
}

VS Code with MCP Extension

Install the MCP extension and add to settings:

{
  "mcp.servers": {
    "alpacon": {
      "command": "uvx",
      "args": ["alpacon-mcp"]
    }
  }
}

Note: Token configuration is automatically discovered from:

  1. ~/.alpacon-mcp/token.json (global - recommended)
  2. ./config/token.json (project-local)
  3. Environment variables

๐Ÿ’ฌ Usage Examples

Server Health Monitoring

"Give me a comprehensive health check for server web-01 including CPU, memory, and disk usage for the last 24 hours"

Performance Analysis

"Show me the top 5 servers with highest CPU usage and analyze performance trends"

System Administration

"List all users who can login on server web-01 and check for any users with sudo privileges"

Automated Troubleshooting

"Server web-01 is responding slowly. Help me investigate CPU, memory, disk I/O, and network usage to find the bottleneck"

Command Execution

"Execute 'systemctl status nginx' on server web-01 and check the service logs"

File Management

"Upload my config.txt file to /home/user/ on server web-01 and then download the logs folder as a zip"

Persistent Shell Sessions

"Create a persistent shell connection to server web-01 and run these commands: check disk usage, list running processes, and create a backup directory"

๐Ÿ”ง Available Tools

๐Ÿ–ฅ๏ธ Server Management

  • servers_list - List all servers in workspace
  • server_get - Get detailed server information
  • server_notes_list - View server documentation
  • server_note_create - Create server notes

๐Ÿ“Š Monitoring & Metrics

  • get_cpu_usage - CPU utilization metrics
  • get_memory_usage - Memory consumption data
  • get_disk_usage - Disk space and I/O metrics
  • get_network_traffic - Network bandwidth usage
  • get_server_metrics_summary - Comprehensive health overview
  • get_cpu_top_servers - Identify performance leaders

๐Ÿ’ป System Information

  • get_system_info - Hardware specifications and details
  • get_os_version - Operating system information
  • list_system_users - User account management
  • list_system_groups - Group membership details
  • list_system_packages - Installed software inventory
  • get_network_interfaces - Network configuration
  • get_disk_info - Storage device information

๐Ÿ”ง Remote Operations

Websh (Shell Access)

  • websh_session_create - Create secure shell sessions
  • websh_command_execute - Execute single commands
  • websh_websocket_execute - Single command via WebSocket
  • websh_channel_connect - Persistent connection management
  • websh_channel_execute - Execute commands using persistent channels
  • websh_channels_list - List active WebSocket channels
  • websh_session_terminate - Close sessions

WebFTP (File Management)

  • webftp_upload_file - Upload files using S3 presigned URLs
  • webftp_download_file - Download files/folders (folders as .zip)
  • webftp_uploads_list - Upload history
  • webftp_downloads_list - Download history
  • webftp_sessions_list - Active FTP sessions

๐Ÿ“‹ Event Management

  • list_events - Browse server events and logs
  • search_events - Find specific events
  • acknowledge_command - Confirm command receipt
  • finish_command - Mark commands as complete

๐Ÿ” Identity and Access Management (IAM)

User Management:

  • iam_users_list - List workspace IAM users with pagination
  • iam_user_get - Get detailed user information
  • iam_user_create - Create new users with group assignment
  • iam_user_update - Update user details and group memberships
  • iam_user_delete - Remove users from workspace
  • iam_user_permissions_get - View effective user permissions
  • iam_user_assign_role - Assign roles to users

Group & Role Management:

  • iam_groups_list - List all workspace groups
  • iam_group_create - Create groups with permissions
  • iam_roles_list - List available roles
  • iam_permissions_list - View all permissions

Advanced IAM Features:

  • Workspace-level isolation for multi-tenant security
  • Role-based access control (RBAC) implementation
  • Group-based permission inheritance
  • Comprehensive audit trails and logging

๐Ÿ” Authentication

  • auth_set_token - Configure API tokens
  • auth_remove_token - Remove stored tokens

๐ŸŒ Supported Platforms

Platform Status Notes
Claude Desktop โœ… Full Support Recommended client
Cursor IDE โœ… Full Support Native MCP integration
VS Code โœ… Full Support Requires MCP extension
Continue โœ… Full Support Via MCP protocol
Other MCP Clients โœ… Compatible Standard protocol support

๐Ÿ“– Documentation

๐Ÿš€ Advanced Usage

Multi-Workspace Management

# Configure tokens for multiple workspaces (ap1 region)
python -c "
from utils.token_manager import TokenManager
tm = TokenManager()
tm.set_token('ap1', 'company-prod', 'ap1-company-prod-token')
tm.set_token('ap1', 'company-staging', 'ap1-company-staging-token')
tm.set_token('ap1', 'company-dev', 'ap1-company-dev-token')
"

Custom Config File

# Use custom config file location
export ALPACON_MCP_CONFIG_FILE="/path/to/custom-tokens.json"
uvx alpacon-mcp

Docker Deployment

# Build and run with Docker
docker build -t alpacon-mcp .
docker run -v $(pwd)/config:/app/config:ro alpacon-mcp

SSE Mode (HTTP Transport)

# Run in Server-Sent Events mode for web integration
python main_sse.py
# Server available at http://localhost:8237

๐Ÿ”’ Security & Best Practices

  • Secure Token Storage - Tokens encrypted and never committed to git
  • Workspace-Based Access Control - Separate tokens per workspace environment
  • ACL Configuration Required - Configure token permissions in Alpacon web interface for command execution
  • Audit Logging - All operations logged for security review
  • Connection Validation - API endpoints verified before execution

โš ๏ธ Command Execution Limitations

Important: Websh and command execution tools can only run pre-approved commands configured in your token's ACL settings:

  1. Visit token details in Alpacon web interface (click on your token)
  2. Configure ACL permissions for allowed commands, servers, and operations
  3. Commands not in ACL will be rejected with 403/404 errors
  4. Contact your administrator if you need additional command permissions

๐Ÿค Contributing

We welcome contributions! Please see our Contributing Guide for details.

  • ๐Ÿ› Bug Reports - Use GitHub issues
  • ๐Ÿ’ก Feature Requests - Open discussions
  • ๐Ÿ“ Documentation - Help improve guides
  • ๐Ÿ”ง Code Contributions - Submit pull requests

๐Ÿ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.


Ready to transform your server management experience?

Built with โค๏ธ for the Alpacon ecosystem

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

alpacon_mcp-0.4.1.tar.gz (153.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

alpacon_mcp-0.4.1-py3-none-any.whl (198.9 kB view details)

Uploaded Python 3

File details

Details for the file alpacon_mcp-0.4.1.tar.gz.

File metadata

  • Download URL: alpacon_mcp-0.4.1.tar.gz
  • Upload date:
  • Size: 153.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for alpacon_mcp-0.4.1.tar.gz
Algorithm Hash digest
SHA256 87d63204bfa07d3d5bddca88643f1318bb73f68a5f1867a6856d9a7d34198959
MD5 74708d12c2c0e5cdd551db94ada33d24
BLAKE2b-256 5b46237f9996c1382761330e83fd14c68e2cb53f2b7db66677732b7d53b40f1b

See more details on using hashes here.

Provenance

The following attestation bundles were made for alpacon_mcp-0.4.1.tar.gz:

Publisher: publish.yml on alpacax/alpacon-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file alpacon_mcp-0.4.1-py3-none-any.whl.

File metadata

  • Download URL: alpacon_mcp-0.4.1-py3-none-any.whl
  • Upload date:
  • Size: 198.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for alpacon_mcp-0.4.1-py3-none-any.whl
Algorithm Hash digest
SHA256 ce68cc48cdc39025b030e39f389060e38e1ffd16e1495706c87849d77adcf642
MD5 7abb168a7ceb5155b5bec40c6f54423d
BLAKE2b-256 568906530bb0b47666e2dd8bdfd21ec5b3357d9731bc3ccf773e6fd60748473b

See more details on using hashes here.

Provenance

The following attestation bundles were made for alpacon_mcp-0.4.1-py3-none-any.whl:

Publisher: publish.yml on alpacax/alpacon-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page