Sprite MCP Server
The Sprite MCP Server enables comprehensive management of Sprite VMs through an MCP-compatible client like Claude, with interactive UI dashboards for visual management.
List & Manage VMs – View all Sprite VMs via an interactive visual dashboard, create new VMs by name, and destroy existing ones (with a required confirmation flag for safety)
Execute Commands – Run shell commands on remote Sprite VMs via a terminal UI with command history and configurable timeouts
Checkpoint Management – Create filesystem snapshots (with optional comments), list existing checkpoints, and restore a VM to a previous checkpoint state
File Transfer – Upload local files to a Sprite VM (
push_file) or download files from a Sprite VM to local storage (fetch_file)Session Management – List all active sessions running on a specific Sprite VM
Get VM URL – Retrieve the public URL for a specific Sprite VM
Interactive UIs – Visual dashboard and terminal interfaces integrate directly into Claude conversations for a seamless management experience
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Sprite MCP Server show my active sprites and open the interactive dashboard"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Sprite MCP Server
MCP server for managing Sprite VMs with interactive UI dashboards (MCP Apps).
Works with Claude.ai, Claude Desktop, Claude Code, VS Code, and any MCP-compatible client.
Features
List & manage Sprite VMs - Interactive dashboard with status indicators
Execute commands - Terminal UI with command history
Checkpoints - Create, list, restore filesystem snapshots
File transfer - Push/pull files to/from remote sprites
Session management - List, attach, kill sessions
Related MCP server: MCP VPS Manager
Windows Setup (Claude Desktop / Claude Code)
Prerequisites
Node.js 20+ - Download from nodejs.org
Git - Download from git-scm.com
Sprite CLI - Get your token from sprites.dev
Step 1: Install Sprite CLI
Download and install the Sprite CLI for Windows:
# Using PowerShell (run as Administrator)
irm https://sprites.dev/install.ps1 | iexOr download manually from sprites.dev/downloads.
Step 2: Authenticate with Sprite
Get your API token from the Sprites dashboard, then:
# Authenticate with your token
sprite auth setup --token "your-org/org-id/token-id/token-value"
# Or use interactive login (opens browser)
sprite loginVerify it works:
sprite listStep 3: Clone and Build the MCP Server
# Clone the repository
git clone https://github.com/Anansitrading/sprite-mcp-server.git
cd sprite-mcp-server
# Install dependencies
npm install
# Build the server
npm run buildStep 4: Find Your Sprite CLI Path
# Find where sprite is installed
where spriteThis typically returns something like:
C:\Users\YourName\.local\bin\sprite.exeC:\Users\YourName\AppData\Local\Programs\sprite\sprite.exe
Note this path - you'll need it for configuration.
Step 5: Configure Claude Desktop
Edit your Claude Desktop config file:
Location: %APPDATA%\Claude\claude_desktop_config.json
Open it with:
notepad "$env:APPDATA\Claude\claude_desktop_config.json"Add this configuration (replace paths with your actual paths):
{
"mcpServers": {
"sprite": {
"command": "node",
"args": ["C:\\Users\\YourName\\sprite-mcp-server\\dist\\index.js"],
"env": {
"SPRITE_BIN": "C:\\Users\\YourName\\.local\\bin\\sprite.exe"
}
}
}
}Important: Use double backslashes (\\) in paths or forward slashes (/).
Step 6: Restart Claude Desktop
Fully quit Claude Desktop (check system tray)
Reopen Claude Desktop
Look for the hammer icon (🔨) indicating MCP tools are available
Step 7: Test It
Ask Claude:
"List my sprites"
"Execute
ls -laon my sprite""Create a checkpoint"
Claude Code Setup (Windows)
For Claude Code CLI, add to your settings:
# Open Claude Code settings
claude mcp add sprite -- node "C:\Users\YourName\sprite-mcp-server\dist\index.js"Or edit ~/.claude/settings.json:
{
"mcpServers": {
"sprite": {
"command": "node",
"args": ["C:\\Users\\YourName\\sprite-mcp-server\\dist\\index.js"],
"env": {
"SPRITE_BIN": "C:\\Users\\YourName\\.local\\bin\\sprite.exe"
}
}
}
}Linux/macOS Setup
Prerequisites
Node.js 20+
Sprite CLI configured with credentials
Quick Start
# Clone & build
git clone https://github.com/Anansitrading/sprite-mcp-server.git
cd sprite-mcp-server
npm install
npm run build
# Authenticate with Sprite
sprite login
# or
sprite auth setup --token "your-token"
# Test
sprite listClaude Desktop Configuration
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"sprite": {
"command": "node",
"args": ["/path/to/sprite-mcp-server/dist/index.js"],
"env": {
"SPRITE_BIN": "/home/youruser/.local/bin/sprite"
}
}
}
}Claude Code Configuration
claude mcp add sprite -- node /path/to/sprite-mcp-server/dist/index.jsServer Deployment (for Claude.ai web)
For hosting your own MCP server accessible from claude.ai:
Prerequisites
Node.js 20+
A domain pointing to your server (for HTTPS)
Caddy or nginx for reverse proxy
Deploy
# Clone & build
git clone https://github.com/Anansitrading/sprite-mcp-server.git
cd sprite-mcp-server
npm install
npm run build
# Configure
cp .env.example .env
# Edit .env:
# PORT=3847
# SPRITE_BIN=/home/sprite/.local/bin/sprite
# Run with systemd
sudo cp sprite-mcp.service /etc/systemd/system/
sudo systemctl daemon-reload
sudo systemctl enable sprite-mcp
sudo systemctl start sprite-mcpCaddy Reverse Proxy
mcp.yourdomain.com {
reverse_proxy localhost:3847
}Connect to Claude.ai
Add MCP Server:
Name:
sprite-mcpURL:
https://mcp.yourdomain.com/sse
Test by asking Claude: "List my sprites"
MCP Tools
Tool | Description |
| List all Sprite VMs (with interactive dashboard) |
| Execute command on a sprite (with terminal UI) |
| Create filesystem snapshot |
| List available checkpoints |
| Restore to a checkpoint |
| Get sprite's public URL |
| Download file from sprite |
| Upload file to sprite |
| List active sessions |
| Create new sprite VM |
| Delete a sprite VM |
Interactive UIs (MCP Apps)
This server uses MCP Apps to provide interactive interfaces:
Dashboard (
ui://sprite/dashboard) - Visual sprite managementTerminal (
ui://sprite/terminal) - Command execution interface
These render directly in the Claude conversation when using supported clients.
Troubleshooting
Windows: "sprite is not recognized"
Add Sprite to your PATH or use the full path in SPRITE_BIN:
# Find sprite location
where sprite
# Add to PATH (PowerShell, run as admin)
$env:Path += ";C:\Users\YourName\.local\bin"
[Environment]::SetEnvironmentVariable("Path", $env:Path, [EnvironmentVariableTarget]::User)Windows: "ENOENT" or "spawn error"
Ensure all paths use double backslashes or forward slashes
Verify the
dist/index.jsfile exists (runnpm run buildfirst)Check that
SPRITE_BINpoints to the actual.exefile
"Sprite CLI not authenticated"
# Re-authenticate
sprite login
# Or with token
sprite auth setup --token "your-token"
# Verify
sprite listCheck server health
# If running HTTP server
curl http://localhost:3847/healthTest MCP handshake
echo '{"jsonrpc":"2.0","method":"tools/list","params":{},"id":1}' | npm startArchitecture
┌─────────────────────────────────────────────────────────┐
│ Claude.ai / Desktop │
├─────────────────────────────────────────────────────────┤
│ MCP Protocol │
│ (stdio or HTTP/SSE transport) │
├─────────────────────────────────────────────────────────┤
│ sprite-mcp-server │
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────────┐ │
│ │ MCP Tools │ │ UI Resources│ │ Sprite CLI │ │
│ │ (11 tools) │ │ (Dashboard) │ │ Integration │ │
│ └─────────────┘ └─────────────┘ └─────────────────┘ │
├─────────────────────────────────────────────────────────┤
│ Sprite CLI │
│ (sprite list, exec, checkpoint...) │
├─────────────────────────────────────────────────────────┤
│ Sprites API / VMs │
└─────────────────────────────────────────────────────────┘License
MIT
Available Tools
11 toolscreate_checkpointB
Create a filesystem checkpoint/snapshot of a Sprite VM for quick restore
Inputs: sprite (required), comment, org.
create_spriteC
Create a new Sprite VM
Inputs: name (required), org.
destroy_spriteA
Destroy/delete a Sprite VM (requires confirmation)
Inputs: sprite (required), confirm (required), org.
exec_commandC
Execute a command on a remote Sprite VM
Inputs: sprite (required), command (required), org, timeout.
fetch_fileA
Download a file from a remote Sprite VM to the local filesystem
Inputs: sprite (required), remote_path (required), local_path (required), org.
get_sprite_urlB
Get the public URL for a Sprite VM
Inputs: sprite (required), org.
list_checkpointsC
List all checkpoints for a Sprite VM
Inputs: sprite (required), org.
list_sessionsC
List active sessions on a Sprite VM
Inputs: sprite (required), org.
list_spritesC
List all available Sprite VMs in the organization. Returns an interactive dashboard to manage sprites.
Inputs: org.
push_fileC
Upload a file from local filesystem to a remote Sprite VM
Inputs: sprite (required), local_path (required), remote_path (required), org.
restore_checkpointC
Restore a Sprite VM to a previous checkpoint state
Inputs: sprite (required), checkpoint_id (required), org.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Every tool has a clearly distinct purpose with no ambiguity. For example, create_sprite, destroy_sprite, and list_sprites handle VM lifecycle management, while fetch_file and push_file handle file transfers, and checkpoint tools manage snapshots. The descriptions clearly differentiate each tool's specific function.
All tools follow a consistent verb_noun naming pattern throughout (e.g., create_checkpoint, list_sessions, push_file). There are no deviations in style or convention, making the tool set predictable and easy to understand.
With 11 tools, this is well-scoped for managing Sprite VMs. Each tool earns its place by covering essential operations like VM lifecycle, file management, checkpointing, and session monitoring without being excessive or insufficient.
The tool surface provides complete coverage for the Sprite VM domain, including CRUD operations (create, list, destroy), file management (push, fetch), checkpoint lifecycle (create, list, restore), and additional utilities (exec_command, get_sprite_url, list_sessions). There are no obvious gaps that would hinder agent workflows.
Maintenance
Related MCP Connectors
Provides capabilities that let LLM agents perform a range of infrastructure management tasks.
Linux VMs for AI agents: create VMs, run commands, edit files and open preview URLs.
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Cloud desktops for AI agents: create a Linux computer, see its screen, click, type and run tasks.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables AI assistants to run, manage, and debug BSD/Illumos VMs through natural language. Supports creating FreeBSD, OpenBSD, NetBSD, and OmniOS VMs, executing commands inside them, accessing console logs, and managing snapshots.71MIT
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to securely manage Virtual Private Servers via SSH, with features including command execution, file operations, system monitoring, and service management.2MIT
- FlicenseAqualityDmaintenanceGives AI assistants full control over a VPS via SSH, enabling command execution, file management, service control, Docker and firewall management.96-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to manage virtual machines via natural language, including creating, editing, and VNC control.9 npmMIT