Which integrations are available for this server?

Enables interaction with a Linux desktop environment using X11, providing tools for screen capture, mouse control (clicking, dragging, scrolling), keyboard input, and retrieving display information.

How do I use Computer Use MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Computer Use MCP Server take a screenshot and tell me what's on my screen" 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.

Computer Use MCP Server

by SebastianBaltes

Overview Schema Source Related Servers Discussions Admin

Python

Local

Computer Use MCP Server for Claude Code

An MCP (Model Context Protocol) server that gives Claude Code the ability to see and interact with your Linux desktop — take screenshots, click, type, scroll, drag, and more.

Built on top of xdotool, scrot, and ImageMagick. Designed to run as a stdio MCP server inside Claude Code.

Features

Screenshots — full desktop capture, automatically scaled to fit API constraints
Mouse control — left/right/middle/double/triple click, drag, move, scroll
Keyboard input — type text, press key combinations, hold keys
Screen zoom — capture a region at full (unscaled) resolution for reading small text
Display info — query resolution, scale factor, and coordinate space

All coordinates use a scaled coordinate space that maps to the actual screen resolution. The server handles the conversion transparently.

Related MCP server: linux-computer-use

Prerequisites

Linux with X11 (Wayland is not supported)
Python >= 3.10
System packages:
```
sudo apt install xdotool scrot imagemagick x11-utils
```
Note: xdpyinfo is part of the x11-utils package on Debian/Ubuntu — there is no standalone xdpyinfo package.

Installation

git clone https://github.com/SebastianBaltes/claude_code_computer_use_mcp.git
cd claude_code_computer_use_mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -e .

Claude Code Configuration

The easiest way is to use the Claude Code CLI:

claude mcp add computer-use --scope user -- /path/to/claude_code_computer_use_mcp/.venv/bin/python -m computer_use_mcp.server

Replace /path/to/ with your actual clone path. Then restart Claude Code — the computer_* tools will be available automatically.

Alternatively, add the server manually to ~/.claude.json under mcpServers:

{
  "mcpServers": {
    "computer-use": {
      "type": "stdio",
      "command": "/path/to/claude_code_computer_use_mcp/.venv/bin/python",
      "args": ["-m", "computer_use_mcp.server"],
      "env": {}
    }
  }
}

Note: The valid --scope values are local, user, project, dynamic, enterprise, claudeai, and managed. Use user for a personal installation available across all projects.

Available Tools

Tool	Description
`computer_screenshot`	Capture the full desktop
`computer_left_click`	Left-click (with optional modifier key)
`computer_right_click`	Right-click
`computer_double_click`	Double-click
`computer_triple_click`	Triple-click (select line)
`computer_middle_click`	Middle-click
`computer_mouse_move`	Move cursor without clicking
`computer_left_click_drag`	Click and drag
`computer_type`	Type a text string
`computer_key`	Press a key or key combo (e.g. `ctrl+s`)
`computer_scroll`	Scroll in any direction
`computer_hold_key`	Hold a key for N seconds
`computer_wait`	Pause for N seconds
`computer_cursor_position`	Get current cursor position
`computer_zoom`	Capture a screen region at full resolution
`computer_display_info`	Get display resolution and scale info

How It Works

The server detects the screen resolution via xdpyinfo and calculates a scale factor to keep screenshots within Anthropic's API image constraints (max 1568px long edge, max 1.15M total pixels). All coordinates passed by Claude are in this scaled space and get converted to actual screen coordinates before executing actions.

License

MIT

Available Tools

16 tools

computer_cursor_positionA

Get the current mouse cursor position in scaled coordinates.

Inputs: no named parameters.

computer_display_infoA

Get information about the display: resolution, scale factor, and coordinate space.

Inputs: no named parameters.

computer_double_clickA

Double-click at the given coordinates. The display is 1429x804 pixels (scaled from 1920x1080). All coordinates are in the scaled coordinate space.

Inputs: x (required), y (required).

computer_hold_keyB

Hold down a key for a specified duration in seconds.

Inputs: keys (required), duration (required).

computer_keyA

Press a key or key combination. Use xdotool key names: Return, Tab, Escape, BackSpace, Delete, space, Up, Down, Left, Right, Home, End, Page_Up, Page_Down, F1-F12, ctrl+c, ctrl+v, ctrl+z, alt+F4, super, ctrl+shift+t, etc. Multiple keys can be chained with '+' for combos.

Inputs: keys (required).

computer_left_clickA

Click the left mouse button at the given coordinates. Optionally hold a modifier key (shift, ctrl, alt, super) during the click. The display is 1429x804 pixels (scaled from 1920x1080). All coordinates are in the scaled coordinate space.

Inputs: x (required), y (required), modifier.

computer_left_click_dragA

Click and drag from start coordinates to end coordinates. Useful for drag-and-drop, resizing windows, selecting text regions, etc. The display is 1429x804 pixels (scaled from 1920x1080). All coordinates are in the scaled coordinate space.

Inputs: start_x (required), start_y (required), end_x (required), end_y (required).

computer_middle_clickA

Middle-click at the given coordinates. The display is 1429x804 pixels (scaled from 1920x1080). All coordinates are in the scaled coordinate space.

Inputs: x (required), y (required).

computer_mouse_moveA

Move the mouse cursor to the given coordinates without clicking. The display is 1429x804 pixels (scaled from 1920x1080). All coordinates are in the scaled coordinate space.

Inputs: x (required), y (required).

computer_right_clickA

Right-click at the given coordinates. The display is 1429x804 pixels (scaled from 1920x1080). All coordinates are in the scaled coordinate space.

Inputs: x (required), y (required).

computer_screenshotA

Take a screenshot of the current desktop. Returns the screenshot as a PNG image. The display is 1429x804 pixels (scaled from 1920x1080). All coordinates are in the scaled coordinate space.

Inputs: no named parameters.

computer_scrollA

Scroll at the given coordinates in the specified direction. The display is 1429x804 pixels (scaled from 1920x1080). All coordinates are in the scaled coordinate space.

Inputs: x (required), y (required), direction (required), amount.

computer_triple_clickA

Triple-click at the given coordinates (select a line of text). The display is 1429x804 pixels (scaled from 1920x1080). All coordinates are in the scaled coordinate space.

Inputs: x (required), y (required).

computer_typeA

Type a text string at the current cursor position. The text is typed character by character with a small delay. Use this for entering text into input fields, editors, etc. For special keys or shortcuts, use computer_key instead.

Inputs: text (required).

computer_waitA

Wait/pause for a specified duration in seconds. Useful to let UI settle.

Inputs: duration (required).

computer_zoomA

Capture a specific region of the screen at full (unscaled) resolution. Useful for reading small text or inspecting UI details. Provide top-left (x1, y1) and bottom-right (x2, y2) coordinates of the region. The display is 1429x804 pixels (scaled from 1920x1080). All coordinates are in the scaled coordinate space.

Inputs: x1 (required), y1 (required), x2 (required), y2 (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4/5.0

Scored 2026-05-06 02:50 across 16 tools

Disambiguation5/5

Each tool targets a distinct action (click, double-click, triple-click, drag, scroll, key press, type, etc.) with clear descriptions, avoiding overlap. The only potential confusion among click variants is resolved by explicit naming.

Naming Consistency5/5

All tools follow the 'computer_<action>_<target>' pattern (e.g., computer_left_click_drag, computer_mouse_move). No mixing of naming conventions.

Tool Count5/5

16 tools is well-scoped for a computer control server, covering essential mouse, keyboard, screenshot, and zoom operations without being excessive or sparse.

Completeness4/5

Covers core GUI automation operations thoroughly, but lacks clipboard access or system-level actions (e.g., opening applications). Minor gap for advanced workflows.

Maintenance

ActivityInactive

ResponsivenessLimited data

Resources

Related MCP Connectors

box by Simular
ai.simular
A cloud Linux desktop for your AI: browse, click, type, read the screen and run commands.
Agent Orchestration Browser Automation Command Line
1
https://mcp.box.simular.ai/mcp
BCD — Bridge Control DelegateA
com.snack-wrap.bcd
Use your Mac, Windows or Linux computer from ChatGPT, Claude or Codex: files, commands, documents.
File Systems Command Line Browser Automation
781
https://bcd.snack-wrap.com/mcp
Mandala Computer
io.github.mandalacomputer
Cloud desktops for AI agents: create a Linux computer, see its screen, click, type and run tasks.
Agent Orchestration Virtualization OS Automation
1
https://app.mandala.computer/mcp
GlasswarpA
com.glasswarp
Eyes and hands on real Windows PCs — observe, click, type via Glasswarp API.
OS Automation Autonomous Agents
162
https://mcp.glasswarp.com/mcp

Related MCP Servers

claude-linux-mcp
Shell Access OS Automation
LukeLamb
A
license
A
quality
C
maintenance
Give Claude Desktop full desktop control on Linux/X11: screenshot, mouse, keyboard, windows, clipboard, app launch. Zero-dependency MCP extension, MIT-licensed.
Updated a month ago (2026-10-02 18:20 UTC)
15
MIT
linux-computer-use
OS Automation App Automation
tak-uukti
A
license
Not graded
quality
D
maintenance
Enables AI agents to control Linux/X11 desktops by providing tools for taking screenshots, clicking, typing, and managing windows via AT-SPI and xdotool.
Updated 6 months ago (2026-05-03 10:27 UTC)
3
MIT
screenmcp-claude-plugin
OS Automation Autonomous Agents
shimondoodkin
A
license
Not graded
quality
D
maintenance
Enables Claude to control the local desktop via screenshot, mouse, keyboard, and clipboard operations.
Updated 5 months ago (2026-06-28 17:13 UTC)
MIT
computer-use
OS Automation Autonomous Agents
mikesmullin
A
license
Not graded
quality
C
maintenance
Enables window management, screenshot, typing, and clicking on X11 with multi-monitor support.
Updated 20 days ago (2026-10-25 21:31 UTC)
MIT

Computer Use MCP Server for Claude Code

Features

Prerequisites

Installation

Claude Code Configuration

Available Tools

How It Works

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

claude-linux-mcp

linux-computer-use

screenmcp-claude-plugin

computer-use