
Claude KVM MCP
- 16 repo stars
- Updated July 6, 2026
- ARAS-Workspace/claude-kvm
Claude KVM is an MCP server that controls remote desktops over VNC using a Swift daemon and Apple Vision OCR.
About
Claude KVM is an MCP server that lets coding agents operate a remote computer through VNC, backed by a native Swift daemon and Apple Vision OCR for interpreting what appears on screen. developers who debug GUI-only installers, internal admin panels, or cross-platform apps on a remote Mac or VM can register the npm package and point required environment variables at their VNC endpoint and daemon binary path. It is intentionally heavier than browser MCP tools: you are delegating full desktop interaction, including credentials you supply via VNC_USERNAME and VNC_PASSWORD when needed. Use it in production-adjacent or staging infra when reproducing issues requires seeing and clicking the real UI, not just hitting HTTP APIs. Expect advanced setup—daemon path, network reachability, and secret handling are on you.
- MCP server (npm claude-kvm 2.0.9) drives remote desktops over VNC with a native Swift claude-kvm-daemon
- Apple Vision OCR on captured frames so agents can reason about on-screen text and UI state
- Required env: VNC_HOST, VNC_PORT, CLAUDE_KVM_DAEMON_PATH; optional ARD/VNC username and password secrets
- stdio MCP transport suited to local Claude Code workflows against one controlled remote host
Claude KVM MCP by the numbers
- Data as of Aug 10, 2026 (Skillselion catalog sync)
claude mcp add --env VNC_HOST=YOUR_VNC_HOST --env VNC_PORT=YOUR_VNC_PORT --env VNC_USERNAME=YOUR_VNC_USERNAME --env VNC_PASSWORD=YOUR_VNC_PASSWORD --env CLAUDE_KVM_DAEMON_PATH=YOUR_CLAUDE_KVM_DAEMON_PATH claude-kvm -- npx -y claude-kvmAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| repo stars | ★ 16 |
|---|---|
| Package | claude-kvm |
| Transport | STDIO |
| Auth | Required |
| Last updated | July 6, 2026 |
| Repository | ARAS-Workspace/claude-kvm ↗ |
What it does
Give your agent VNC-driven control of a remote desktop with OCR-backed screen understanding for reproducing bugs or running GUI-only tools.
Who is it for?
Advanced developers operating remote Mac or VM desktops who need agent-driven VNC sessions for support, QA, or legacy GUI tooling.
Skip if: Simple website testing (use browser MCP), headless CI-only pipelines, or hosts where you cannot install the claude-kvm-daemon binary.
What you get
After configuration, your agent can view and interact with the remote desktop through MCP with OCR-assisted screen understanding.
- Agent-driven VNC session control exposed as MCP tools
- Screen captures interpreted with Apple Vision OCR via the Swift daemon
By the numbers
- npm package claude-kvm version 2.0.9 with stdio transport
- Five documented environment variables including required VNC_HOST, VNC_PORT, and CLAUDE_KVM_DAEMON_PATH
- Repository: github.com/ARAS-Workspace/claude-kvm
README.md
Claude KVM
Remote Access, Artificial Intelligence
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
Recommended MCP Servers
How it compares
Full VNC desktop MCP with native OCR daemon, not a lightweight Playwright-style browser skill.
FAQ
Who is Claude KVM MCP for?
Technical developers and operators who already use VNC to reach remote machines and want Claude Code to drive those sessions via MCP.
When should I use Claude KVM MCP?
Use it during operate and infra work when reproducing or fixing issues requires interacting with a remote GUI the agent cannot reach through APIs alone.
How do I add Claude KVM MCP to my agent?
Install claude-kvm from npm (2.0.9), set VNC_HOST, VNC_PORT, and CLAUDE_KVM_DAEMON_PATH, add VNC credentials if required, and register the package as a stdio MCP server in Claude Code or a compatible client.

