Claude KVM MCP Server
io.github.ARAS-Workspace/claude-kvm
Control remote desktops via VNC with AI—native Swift daemon and Apple Vision OCR for precise automation.
What is the Claude KVM MCP server?
Claude KVM is an MCP server that enables Claude to control remote desktop environments over VNC using a native Swift daemon and Apple Vision OCR. It provides screen capture, mouse/keyboard input, and on-device text detection for AI-driven desktop automation tasks.
Claude KVM lets Claude interact with remote desktops as if using a mouse and keyboard. It captures screenshots, detects UI elements via OCR, and executes clicks, typing, and other input commands. This enables Claude to automate desktop workflows, test applications, and interact with remote systems—all with precise coordinate scaling and progressive verification to minimize token usage.
How to install Claude KVM
Copy-paste configuration for popular MCP clients.
VNC_HOSTrequiredVNC server hostname or IP
VNC_PORTrequiredVNC server port
VNC_USERNAMEsecretVNC/ARD username
VNC_PASSWORDsecretVNC/ARD password
CLAUDE_KVM_DAEMON_PATHrequiredPath to claude-kvm-daemon binary
Tools & capabilities
Tools this server exposes to the agent.
screenshot— Full screen PNG capture of the remote desktopcursor_crop— Crop around cursor with crosshair overlay for focused inspectiondiff_check— Detect screen changes against a saved baselineset_baseline— Save current screen as a reference for diff detectionmouse_click— Click at specified coordinates (left, right, or middle button)mouse_double_click— Double-click at specified coordinatesmouse_move— Move cursor to specified coordinateshover— Move cursor and settle with a wait periodnudge— Relative cursor movement by delta x/ymouse_drag— Drag from one coordinate to anotherscroll— Scroll in a direction (up/down/left/right) by amountkey_tap— Single key press (enter, escape, tab, space, etc.)key_combo— Modifier key combinations (e.g., cmd+c, shift+3)key_type— Type text character by characterpaste— Paste text via clipboarddetect_elements— OCR text detection with bounding boxes using Apple Vision frameworkconfigure— Adjust timing and display parameters at runtimeget_timing— Inspect current timing and display configuration values
Use cases
- Automate desktop workflows and repetitive tasks on remote macOS systems
- Test applications and UI interactions by having Claude interact with the desktop like a user
- Perform web browsing and form-filling tasks on remote systems with visual feedback
- Execute complex multi-step procedures that require visual verification between steps
- Control remote machines for demonstrations, debugging, or system administration
Claude KVM MCP server FAQ
Claude KVM is an MCP server that gives Claude the ability to control remote desktops over VNC. It includes a JavaScript MCP proxy and a native Swift daemon that handles VNC connections, screen capture, and input injection, plus Apple Vision OCR for detecting UI text.
The README does not specify pricing. The project is open-source on GitHub; check the repository for licensing details.
Install the daemon via Homebrew (`brew install claude-kvm-daemon`), then configure your `.mcp.json` file with VNC connection details (host, port, credentials) and the daemon path. Use `npx claude-kvm` as the command in your MCP configuration.
You need VNC server credentials: `VNC_HOST`, `VNC_PORT`, `VNC_USERNAME` (required for Apple Remote Desktop), and `VNC_PASSWORD`. These are set as environment variables in your MCP configuration.
Claude KVM requires macOS with Apple Silicon (aarch64) and Node.js LTS. The native daemon is compiled for Apple Silicon only.
Yes. Use the `configure` method to adjust click hold duration, drag speed, scroll timing, and display scaling (`max_dimension`). Use `get_timing` to inspect current values. All settings can be reset to defaults.
README (reference)
Source of truth, from the repository.
Claude KVM is an MCP tool that controls remote desktop environments over VNC. It consists of a thin JS proxy layer (MCP server) and a platform-native Swift VNC daemon running on your macOS system.
[!TIP] Phantom-WG could be a great alternative for you. Isolate your VNC server within your own network while enjoying self-hosted VPN performance with the extra privacy features you gain along the way.
Live Test Runs
- Integration Test
- Mac Integration Test
- Mac Calculator Test
- Mac Scientific Calculator Test
- Mac Safari Browsing Test
- Mac Drag & Drop Test
- Mac Chess Test
- Mac Chess Direct Test
- Mac Phantom-WG Install Test
[!NOTE] Tests are conducted transparently on GitHub Actions — each step is visible in the CI environment. At the end of every test, whether the integration passes or fails, you'll find screenshots of each step the agent took during the session, along with an
.mp4video recording that captures the entire session. By reviewing these recordings and screenshots, you can observe how the agent progressed through each stage, how long the task took, and what decisions were made based on the system prompt. You can use these examples as a reference when crafting your own system prompts or instructions for the MCP server in your own environment.
[!WARNING] Artifacts attached to these runs may have expired due to GitHub's artifact retention policy. Persistent copies are prepared via the Persist Artifacts workflow and can always be accessed by run ID from the
artifacts/directory on the press-kit branch.
Architecture
graph TB
subgraph MCP["MCP Client (Claude)"]
AI["Claude"]
end
subgraph Proxy["claude-kvm · MCP Proxy (stdio)"]
direction TB
Server["MCP Server<br/><code>index.js</code>"]
Tools["Tool Definitions<br/><code>tools/index.js</code>"]
Server --> Tools
end
subgraph Daemon["claude-kvm-daemon · Native VNC Client (stdin/stdout)"]
direction TB
CMD["Command Handler<br/><i>PC Dispatch</i>"]
Scale["Display Scaling<br/><i>Scaled ↔ Native</i>"]
subgraph Screen["Screen"]
Capture["Frame Capture<br/><i>PNG · Crop · Diff</i>"]
OCR["OCR Detection<br/><i>Apple Vision</i>"]
end
subgraph InputGroup["Input"]
Mouse["Mouse<br/><i>Click · Drag · Move · Scroll</i>"]
KB["Keyboard<br/><i>Tap · Combo · Type · Paste</i>"]
end
VNC["VNC Bridge<br/><i>LibVNCClient 0.9.15</i>"]
CMD --> Scale
Scale --> Capture
Scale --> Mouse
Scale --> KB
Capture -.->|"framebuffer"| VNC
Mouse -->|"pointer events"| VNC
KB -->|"key events"| VNC
end
subgraph Target["Target Machine"]
VNC_Server["VNC Server<br/><i>:5900</i>"]
Desktop["Desktop Environment"]
VNC_Server --> Desktop
end
AI <-->|"stdio<br/>JSON-RPC"| Server
Server <-->|"stdin/stdout<br/>PC (NDJSON)"| CMD
VNC <-->|"RFB Protocol<br/>TCP :5900"| VNC_Server
classDef proxy fill:#1a1a2e,stroke:#16213e,color:#e5e5e5
classDef daemon fill:#0f3460,stroke:#533483,color:#e5e5e5
classDef target fill:#1a1a2e,stroke:#e94560,color:#e5e5e5
class Server,Tools proxy
class CMD,Scale,VNC,Capture,Mouse,KB daemon
class VNC_Server,Desktop target
Layers
| Layer | Language | Role | Communication |
|---|---|---|---|
| MCP Proxy | JavaScript (Node.js) | Communicates with Claude over MCP protocol, manages daemon lifecycle | stdio JSON-RPC |
| VNC Daemon | Swift/C (Apple Silicon) | VNC connection, screen capture, mouse/keyboard input injection | stdin/stdout PC (NDJSON) |
PC (Procedure Call) Protocol
Communication between the proxy and daemon uses the PC protocol over NDJSON:
Request: {"method":"<name>","params":{...},"id":<int|string>}
Response: {"result":{...},"id":<int|string>}
Error: {"error":{"code":<int>,"message":"..."},"id":<int|string>}
Notification: {"method":"<name>","params":{...}}
Coordinate Scaling
The VNC server's native resolution is scaled down to fit within --max-dimension (default: 1280px). Claude works more consistently with scaled coordinates — the daemon handles the conversion in the background:
Native: 4220 x 2568 (VNC server framebuffer)
Scaled: 1280 x 779 (what Claude sees and targets)
mouse_click(640, 400) → VNC receives (2110, 1284)
Screen Strategy
Claude minimizes token cost with a progressive verification approach:
diff_check → changeDetected: true/false ~5ms (text only, no image)
detect_elements → OCR text + bounding boxes ~50ms (text only, no image)
cursor_crop → crop around cursor ~50ms (small image)
screenshot → full screen capture ~200ms (full image)
detect_elements uses Apple Vision framework for on-device OCR. Returns text content with bounding box coordinates in scaled space — enables precise click targeting without consuming vision tokens.
Installation
Requirements
- macOS (Apple Silicon / aarch64)
- Node.js (LTS)
Daemon
brew tap ARAS-Workspace/tap
brew install claude-kvm-daemon
[!NOTE]
claude-kvm-daemonis compiled and code-signed via CI (GitHub Actions). The build output is packaged in two formats: a.tar.gzarchive for Homebrew distribution and a.dmgdisk image for notarization. The DMG is submitted to Apple servers for notarization within the same workflow — the process can be tracked from CI logs. The notarized DMG is available as a CI Artifact; the archived.tar.gzis also published as a release on the repository. Homebrew installation tracks this release.
MCP Configuration
Create a .mcp.json file in your project directory:
{
"mcpServers": {
"claude-kvm": {
"command": "npx",
"args": ["-y", "claude-kvm"],
"env": {
"VNC_HOST": "192.168.1.100",
"VNC_PORT": "5900",
"VNC_USERNAME": "user",
"VNC_PASSWORD": "pass",
"CLAUDE_KVM_DAEMON_PATH": "/opt/homebrew/bin/claude-kvm-daemon",
"CLAUDE_KVM_DAEMON_PARAMETERS": "-v"
}
}
}
}
[!NOTE] The tool is end-to-end tested via CI — Claude executes tasks over VNC while an independent vision model observes and verifies the results. See the Integration Test for live workflow runs, system prompts, and demo recordings.
Configuration
MCP Proxy (ENV)
| Parameter | Default | Description |
|---|---|---|
VNC_HOST | 127.0.0.1 | VNC server address |
VNC_PORT | 5900 | VNC port number |
VNC_USERNAME | Username (required for ARD) | |
VNC_PASSWORD | Password | |
CLAUDE_KVM_DAEMON_PATH | claude-kvm-daemon | Daemon binary path (not needed if already in PATH) |
CLAUDE_KVM_DAEMON_PARAMETERS | Additional CLI arguments for the daemon |
Daemon Parameters (CLI)
Additional arguments passed to the daemon via CLAUDE_KVM_DAEMON_PARAMETERS:
"CLAUDE_KVM_DAEMON_PARAMETERS": "--max-dimension 800 -v"
| Parameter | Default | Description |
|---|---|---|
--max-dimension | 1280 | Maximum display scaling dimension (px) |
--connect-timeout | VNC connection timeout (seconds) | |
--bits-per-sample | Bits per pixel sample | |
--no-reconnect | Disable automatic reconnection | |
-v, --verbose | Verbose logging (stderr) |
Runtime Configuration (PC)
All timing and display parameters are configurable at runtime via the configure method. Use get_timing to inspect current values.
Set timing:
{"method":"configure","params":{"click_hold_ms":80,"key_hold_ms":50}}
{"result":{"detail":"OK — changed: click_hold_ms, key_hold_ms"}}
Change display scaling:
{"method":"configure","params":{"max_dimension":960}}
{"result":{"detail":"OK — changed: max_dimension","scaledWidth":960,"scaledHeight":584}}
Reset to defaults:
{"method":"configure","params":{"reset":true}}
{"result":{"detail":"OK — reset to defaults","timing":{"click_hold_ms":50,"combo_mod_ms":10,"cursor_crop_radius":150,"double_click_gap_ms":50,"drag_min_steps":10,"drag_pixels_per_step":20,"drag_position_ms":30,"drag_press_ms":50,"drag_settle_ms":30,"drag_step_ms":5,"hover_settle_ms":400,"key_hold_ms":30,"max_dimension":1280,"paste_settle_ms":30,"scroll_press_ms":10,"scroll_tick_ms":20,"type_inter_key_ms":20,"type_key_ms":20,"type_shift_ms":10},"scaledWidth":1280,"scaledHeight":779}}
Get current values:
{"method":"get_timing"}
{"result":{"timing":{"click_hold_ms":80,"combo_mod_ms":10,"cursor_crop_radius":150,"double_click_gap_ms":50,"drag_min_steps":10,"drag_pixels_per_step":20,"drag_position_ms":30,"drag_press_ms":50,"drag_settle_ms":30,"drag_step_ms":5,"hover_settle_ms":400,"key_hold_ms":50,"max_dimension":1280,"paste_settle_ms":30,"scroll_press_ms":10,"scroll_tick_ms":20,"type_inter_key_ms":20,"type_key_ms":20,"type_shift_ms":10},"scaledWidth":1280,"scaledHeight":779}}
| Parameter | Default | Description |
|---|---|---|
max_dimension | 1280 | Max screenshot dimension |
cursor_crop_radius | 150 | Cursor crop radius (px) |
click_hold_ms | 50 | Click hold duration |
double_click_gap_ms | 50 | Double-click gap delay |
hover_settle_ms | 400 | Hover settle wait |
drag_position_ms | 30 | Pre-drag position wait |
drag_press_ms | 50 | Drag press hold threshold |
drag_step_ms | 5 | Between interpolation pts |
drag_settle_ms | 30 | Settle before release |
drag_pixels_per_step | 20 | Point density per pixel |
drag_min_steps | 10 | Min interpolation steps |
scroll_press_ms | 10 | Scroll press-release gap |
scroll_tick_ms | 20 | Inter-tick delay |
key_hold_ms | 30 | Key hold duration |
combo_mod_ms | 10 | Modifier settle delay |
type_key_ms | 20 | Key hold during typing |
type_inter_key_ms | 20 | Inter-character delay |
type_shift_ms | 10 | Shift key settle |
paste_settle_ms | 30 | Post-clipboard write wait |
Tools
All operations are performed through a single vnc_command tool:
Screen
| Action | Parameters | Description |
|---|---|---|
screenshot | Full screen PNG capture | |
cursor_crop | Crop around cursor with crosshair overlay | |
diff_check | Detect screen changes against baseline | |
set_baseline | Save current screen as diff reference |
Mouse
| Action | Parameters | Description |
|---|---|---|
mouse_click | x, y, button? | Click (left|right|middle) |
mouse_double_click | x, y | Double click |
mouse_move | x, y | Move cursor |
hover | x, y | Move + settle wait |
nudge | dx, dy | Relative cursor movement |
mouse_drag | x, y, toX, toY | Drag from start to end |
scroll | x, y, direction, amount? | Scroll (up|down|left|right) |
Keyboard
| Action | Parameters | Description |
|---|---|---|
key_tap | key | Single key press (enter|escape|tab|space|...) |
key_combo | key or keys | Modifier combo ("cmd+c" or ["cmd","shift","3"]) |
key_type | text | Type text character by character |
paste | text | Paste text via clipboard |
Detection
| Action | Parameters | Description |
|---|---|---|
detect_elements | OCR text detection with bounding boxes (Apple Vision) |
Returns text elements with bounding box coordinates in scaled space:
{"method":"detect_elements"}
{"result":{"detail":"13 elements","elements":[{"confidence":1,"h":9,"text":"Finder","w":32,"x":37,"y":6},{"confidence":1,"h":9,"text":"File","w":15,"x":84,"y":6},{"confidence":1,"h":9,"text":"Edit","w":19,"x":112,"y":6},{"confidence":1,"h":9,"text":"View","w":22,"x":143,"y":6},{"confidence":1,"h":11,"text":"Go","w":15,"x":179,"y":6},{"confidence":1,"h":9,"text":"Window","w":35,"x":207,"y":6},{"confidence":1,"h":11,"text":"Help","w":22,"x":255,"y":6},{"confidence":1,"h":11,"text":"8•","w":26,"x":1161,"y":6},{"confidence":1,"h":9,"text":"Fri Feb 20 22:19","w":80,"x":1189,"y":6},{"confidence":1,"h":9,"text":"Assets","w":32,"x":1202,"y":97},{"confidence":1,"h":9,"text":"Passwords.kdbx","w":74,"x":1181,"y":168},{"confidence":1,"h":93,"text":"PHANTOM","w":633,"x":322,"y":477},{"confidence":1,"h":32,"text":"YOUR SERVER, YOUR NETWORK, YOUR PRIVACY","w":629,"x":325,"y":568}],"scaledHeight":717,"scaledWidth":1280}}
Configuration
| Action | Parameters | Description |
|---|---|---|
configure | {<params>} | Set timing/display params at runtime |
configure | {reset: true} | Reset all params to defaults |
get_timing | Get current timing + display params |
Control
| Action | Parameters | Description |
|---|---|---|
wait | ms? | Wait (default 500ms) |
health | Connection status + display info | |
shutdown | Graceful daemon shutdown |
Authentication
Supported VNC authentication methods:
- VNC Auth — password-based challenge-response (DES)
- ARD — Apple Remote Desktop (Diffie-Hellman + AES-128-ECB)
macOS is auto-detected via the ARD auth type 30 credential request. When detected, Meta keys are remapped to Super (Command key compatibility).
[!NOTE] Running on a bare-metal Mac? See the Mac M1 Preparation Tricks for VNC hardening, SSH tunneling, and session stability tips.
"Claude" is a trademark of Anthropic, PBC. This project is not affiliated with or endorsed by Anthropic.
Copyright (c) 2026 Riza Emre ARAS — MIT License
Related MCP servers
The DNS/SMTP for AI agents: cross-protocol discovery, messaging and transactions. No middleman fees.

AI Pensieve MCP
Search and cross-reference local AI chat history with read-only tools and source citations.
Search VICATOO hotels by traveler needs, features, location, and landmarks with factual evidence.
Give AI agents autonomous virtual card management via x402 and Stellar USDC

CoS Codex Bridge
Operate Codex projects and tasks from a Chief of Staff with scoped access and durable receipts.

Memorix
Local-first shared project memory for AI coding agents across sessions, IDEs, and tools.


