Claude KVM
Claude KVM is an MCP server that lets you remotely control a desktop environment over VNC, providing full mouse, keyboard, screen capture, and OCR capabilities.
Screen Capture & Observation
screenshot— Take a full-screen PNG capturecursor_crop— Capture a cropped region around the cursor with a crosshair overlaydiff_check— Detect whether the screen has changed since the last baseline (fast, no image returned)set_baseline— Save the current screen state as the diff reference point
Mouse Control
mouse_click— Click at (x, y) with left, right, or middle buttonmouse_double_click— Double-click at (x, y)mouse_move/hover/nudge— Move cursor absolutely, with a settle wait, or by relative offsetmouse_drag— Click-drag from one coordinate to anotherscroll— Scroll up, down, left, or right at a position
Keyboard Control
key_tap— Press a single key (enter, escape, tab, space, etc.)key_combo— Press modifier combinations (e.g.cmd+c,ctrl+shift+t)key_type— Type a string character by characterpaste— Paste text via the system clipboard
OCR & Element Detection
detect_elements— Use Apple Vision on-device OCR to detect text elements and return bounding box coordinates (no vision tokens consumed)
Configuration & Timing
configure— Adjust timing and display parameters at runtime (click hold durations, drag speeds, scroll timing, max dimension, etc.) or reset to defaultsget_timing— Retrieve current timing and display scaling configuration
Batch Execution
action_queue— Execute up to 20 ordered actions (mouse, keyboard, scroll, wait, diff, etc.) sequentially in a single call, reducing round-trips
Control & Lifecycle
wait— Pause execution for a specified duration (50ms–10,000ms)health— Check VNC connection status and display infoshutdown— Gracefully shut down the VNC daemon
Task Signaling
task_complete— Signal that the assigned task was successfully accomplished with a summarytask_failed— Signal that the task could not be completed and provide a reason
Click on "Install 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., "@Claude KVMopen Safari and navigate to google.com"
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.
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.

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
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.mp4 video 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.
Artifacts attached to these runs may have expired due to GitHub's artifact retention policy. Persistent copies are prepared via thePersist Artifacts workflow and can always be accessed by run ID from the artifacts/ directory on the press-kit branch.
Related MCP server: mcp-vnc
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 targetLayers
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-daemonclaude-kvm-daemon is compiled and code-signed via CI (GitHub Actions). The build output is packaged in two formats: a .tar.gz archive for Homebrew distribution and a .dmg disk 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.gz is 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"
}
}
}
}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 theIntegration Test for live workflow runs, system prompts, and demo recordings.
Configuration
MCP Proxy (ENV)
Parameter | Default | Description |
|
| VNC server address |
|
| VNC port number |
| Username (required for ARD) | |
| Password | |
|
| Daemon binary path (not needed if already in PATH) |
| 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 |
|
| Maximum display scaling dimension (px) |
| VNC connection timeout (seconds) | |
| Bits per pixel sample | |
| Disable automatic reconnection | |
| 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 screenshot dimension |
|
| Cursor crop radius (px) |
|
| Click hold duration |
|
| Double-click gap delay |
|
| Hover settle wait |
|
| Pre-drag position wait |
|
| Drag press hold threshold |
|
| Between interpolation pts |
|
| Settle before release |
|
| Point density per pixel |
|
| Min interpolation steps |
|
| Scroll press-release gap |
|
| Inter-tick delay |
|
| Key hold duration |
|
| Modifier settle delay |
|
| Key hold during typing |
|
| Inter-character delay |
|
| Shift key settle |
|
| Post-clipboard write wait |
Tools
All operations are performed through a single vnc_command tool:
Screen
Action | Parameters | Description |
| Full screen PNG capture | |
| Crop around cursor with crosshair overlay | |
| Detect screen changes against baseline | |
| Save current screen as diff reference |
Mouse
Action | Parameters | Description |
|
| Click (left|right|middle) |
|
| Double click |
|
| Move cursor |
|
| Move + settle wait |
|
| Relative cursor movement |
|
| Drag from start to end |
|
| Scroll (up|down|left|right) |
Keyboard
Action | Parameters | Description |
|
| Single key press (enter|escape|tab|space|...) |
|
| Modifier combo ("cmd+c" or ["cmd","shift","3"]) |
|
| Type text character by character |
|
| Paste text via clipboard |
Detection
Action | Parameters | Description |
| 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 |
|
| Set timing/display params at runtime |
|
| Reset all params to defaults |
| Get current timing + display params |
Control
Action | Parameters | Description |
|
| Wait (default 500ms) |
| Connection status + display info | |
| 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).
Running on a bare-metal Mac? See theMac 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
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceAn MCP server to control iOS Simulators.Last updated1153MIT
- AlicenseAqualityDmaintenanceAn MCP server that allows AI agents to remotely control Windows, Linux, and macOS systems via VNC. It provides tools for mouse and keyboard interaction, text input, and screen capturing.Last updated64353MIT
- AlicenseAqualityDmaintenanceA macOS-based MCP server that allows for capturing screenshots of displays and windows, as well as recording window activity to MP4 files. It leverages a Swift CLI backend to interact with macOS CoreGraphics and AVFoundation APIs for seamless screen capture management.Last updated7501MIT
- Flicense-qualityDmaintenanceMCP server for macOS desktop automation enabling screenshot, click, type, scroll, and more. Retina-aware, supports CJK text input and multi-monitor, works with any MCP client without API keys.Last updated4
Related MCP Connectors
MCP server for understanding Javascript internals from ECMAScript specification.
A MCP server built for developers enabling Git based project management with project and personal…
An MCP server that let you interact with Cycloid.io Internal Development Portal and Platform
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ARAS-Workspace/claude-kvm'
If you have feedback or need assistance with the MCP directory API, please join our Discord server