"Working with Excel" matching MCP servers:

Lets AI assistants understand what you're working on — current screen content, recent dictation, clipboard, and saved notes — running entirely on your own machine with nothing sent to the cloud.

Enables background window capture and input automation without moving the cursor or stealing focus, working across Windows, Linux X11, and Wayland systems.

Reports the local user's current activity and idle state, including idle duration, idle threshold comparison, and timestamps, so agents can decide whether to wait for user feedback or keep working autonomously. All activity data is collected on-device through operating-system APIs and returned only to the connected MCP client.

A local Windows automation MCP server that lets a KI-Agent safely control the SteuerSparErklärung tax software: inventory and open tax cases, read pages, compare receipts and values, and edit verified working copies, with all ELSTER transmission paths locked tight.

Connects ChatGPT Web to a self-hosted local coding workbench, enabling file editing, shell commands, Git/GitHub operations, multi-workspace management, code review, terminal processes, checkpoints, and optional Docker sandboxing.

Provides tools for obtaining system CPU and memory statistics through FastAPI endpoints exposed via MCP.

Enables execution of shell commands, directory navigation, and interactive program automation through an enhanced command-line interface. Provides tools for running commands, managing working directories, and handling interactive programs using expect/send sequences.

Launch Windows applications by name, alias, or path via MCP, supporting arguments and working directories. Uses Task Scheduler to detach launched processes so they persist independently of the MCP server.

Local-first macOS MCP server for searching files, running approved Shortcuts, managing Homebrew packages, and working with local models, with read-only defaults and optional gated mutations.

A Windows MCP server that gives ChatGPT permission-controlled tools for troubleshooting software, working with files, running diagnostics, and operating the visible desktop.

An MCP server that lets Claude operate your real computer by moving the actual mouse, clicking, typing, and reading the actual screen, working with your own logged-in sessions in any application.

Enables AI assistants to automatically identify which machine they're working with by providing hostname detection and system information including CPU, memory, OS version, and architecture.

Enables remote server control via SSH through Claude, supporting command execution, file transfers, and multi-server management with both standard and streamable HTTP protocols.

A Model Context Protocol server that enables users to execute arbitrary shell commands through a terminal tool. It supports custom working directories, configurable execution timeouts, and safe command parsing using shlex.

Executes privileged commands with mandatory human approval via a TUI prompt, supporting local and remote execution through sudo.

Enables LLM agents to monitor Mac thermals and control fan speed with safety limits enforced by a root daemon.

A TypeScript-based server that enables programmatic management of pseudo-terminal sessions. It allows users to spawn, control, and interact with terminal processes in real-time through the Model Context Protocol.

Enables MCP-speaking clients to control a real desktop via the computer_use tool, including clicking, typing, scrolling, dragging, key combos, app focus, and screen/accessibility capture. It also provides a verdict system that verifies whether input actions had their intended effect, with configurable approval modes.

Enables AI assistants to control mobile and desktop devices with natural language, including running automation tasks, taking screenshots, and managing devices.

Enables AI agents to capture and analyze screenshots of macOS applications, windows, or the entire screen using local (Ollama) or cloud-based AI vision models, with non-intrusive, fast screen capture via Apple's ScreenCaptureKit.