"Information about computer usage" matching MCP servers:

Provides a persistent Docker computer with terminal, file editing, and optional desktop GUI control through a Three.js interface.

A low-level computer-use MCP server that exposes raw desktop control (mouse, keyboard, shell, windows, processes, screenshots, etc.) to MCP clients like Claude Code and Codex.

Enables DeepSeek Harness to operate files on another computer over MCP, including browsing, reading, writing, editing, searching, moving, and recoverable deletion, with optional command execution. It supports Windows and macOS via LAN or Tailscale with directory authorization and logs.

Gives AI agents controlled access to a computer for browsing, editing, searching, and organizing files; creating and extracting zips; running terminal commands; managing background processes; and transferring files. Supports automatic public tunnel access plus options to restrict folders, use read-only mode, disable the terminal, and expire download/upload links.

Runs builds, tests, and benchmarks on a remote compute node via Tailscale and SSH, syncing projects with rsync.

Enables AI assistants to understand lab topologies, follow operational principles, and interact with real network devices through observable terminals while keeping private access information hidden.

Enables ChatGPT to read and edit local text files, apply precise string replacements, and run Bash commands on a user's own macOS or Linux machine through a secure local tunnel without exposing public ports.

Enables MCP-compatible AI clients to securely monitor and manage a self-hosted Linux VPS over SSH, including service status, disk and RAM usage, TLS certificate expiry, fail2ban summaries, and two-step confirmed service restarts or IP unbans.

Enables a coding agent to get short, token-efficient answers about a project through grouped searches, focused symbol or section reads, and bounded read-only script output, with safety limits on paths, secrets, commands, and response size.

Let your AI build and run a whole app on your computer: an online shop, website, booking app or AI helper. It creates the parts, starts them, checks they work and fixes problems.

An MCP server that lets an AI agent use a real terminal the way a person does: type, press keys, click, read the screen, take a screenshot.

An MCP server that gives AI coding assistants a remote_exec tool to run shell commands on a remote computer through a relay, with supervised approval for each command. The remote machine only needs curl and bash, with no SSH access or installed agent required.

A minimal MCP server that exposes a single tool to query local hardware information (OS, CPU, memory, architecture).

Enables Claude Code to interact with Linux X11 desktops by performing mouse actions, keyboard input, and capturing screenshots. It provides a suite of tools for automation tasks such as clicking, typing, and zooming on specific screen regions.

Enables AI agents to control virtual computers through Orgo, supporting computer management, screen actions, shell commands, file operations, streaming, and AI completions.

An MCP server that intelligently filters and compresses tool outputs to reduce context window usage, saving up to 90% of tokens by removing noise such as passing tests and redundant information.

Local-first MCP server and CLI wrapper for AI coding agents. SAGE routes shell commands through a tracked local runner, stores command history on the user’s machine, and returns compressed terminal output to reduce noisy context.

An MCP server that lets AI assistants inspect and control Asterisk and FreeSWITCH PBX systems, enabling natural language queries about live switch status, channels, registrations, and call control.

A local MCP server that lets users control their computer via voice commands, executing CLI tools, searching files, and receiving spoken feedback, with safety gating and confirmation.

An agent-native shell as an MCP server, designed for LLM agents (like Claude Code) to execute commands with structured output, lazy detail retrieval, and effect tracking, minimizing token usage.