"Linux" matching MCP servers:

MCP server enabling AI agents to control a real Linux browser with live view, human takeover, and safety guardrails.

Enables browser automation for LLMs on Linux display servers, supporting web interaction, screenshots, and JavaScript execution in a real browser.

Enables LLMs to capture desktop screenshots and control the mouse and keyboard on Linux, including Wayland, through MCP.

Exposes vLLM capabilities to AI assistants, enabling chat completions, model management, and platform-aware container control with automatic detection of Docker/Podman and GPU availability across Linux, macOS, and Windows.

Enables ChatGPT to securely control a local workstation via an MCP tunnel, exposing 44 tools for file/project editing, git, process supervision, browser automation, and Office document handling across macOS, Linux, and Windows.

Enables parallel agent tasks on disposable Arch Linux drones by providing a local stdio gateway for batch job submission, status monitoring, log retrieval, artifact fetching, and cancellation across SSH-connected runners.

Enables autonomous desktop automation by delegating tasks to vision-based agents operating within cloud-based virtual machine sandboxes. It allows users to manage VMs, execute complex computer tasks, and receive text-based screen summaries across Linux, Windows, and macOS environments.

Hybrid computer-use MCP server that automates browsers and native macOS/Linux apps by fusing accessibility trees, Chrome DevTools Protocol, and vision into one structured context. Exposes four composable tools — cel_see, cel_act, cel_think, cel_perceive — that work with any MCP client and run fully offline via Ollama.