"PocketBase-Cursor-MCP server by Minhdtb" matching MCP servers:

Enables users to record Windows desktop and browser workflows once and generate replayable Cursor Skills, using Playwright MCP and Windows Computer MCP for semantic, non-coordinate replay.

Enables AI agents such as Cursor, Claude, and Codex to read and manage a PiHerder instance through its bearer token API, including server inventory, jobs, and host files.

An open-source MCP server for macOS that lets AI control desktop apps in the background without moving the cursor or stealing focus.

macOS computer-use MCP server enabling AI agents to capture and interact with specific app windows via normalized coordinates, performing background clicks, keyboard input, and typing without taking over the physical cursor.

AI-powered PC management system with 80+ MCP tools for Cursor, Claude, and other AI agents.

MCP server that gives Claude human-like control of a Windows PC with its own virtual cursor, an emergency stop, and a manager UI.

Enables AI assistants and MCP clients to control an auto-clicker, query cursor position, and locate UI elements via image matching or OCR text search.

Enables AI services like Claude and Cursor to remotely control a Mac by executing shell commands, managing files, and running AppleScript for UI automation. Access is secured through OAuth 2.0 authentication and encrypted tunnels to protect remote interactions.

Enables AI models to control a local Windows desktop by moving the cursor, clicking, scrolling, typing Unicode text, sending key chords, and capturing screenshots. Runs natively on Windows with minimal latency and no heavy dependencies such as Python, PyAutoGUI, or Docker.

Enables MCP-capable AI agents such as Claude, Codex, Gemini CLI, Cursor and Zed to design and manage a Stream Deck by reading layouts, building pages and keys, setting icons and wallpapers, managing profiles and taking screenshots to verify their own work. Access is governed by read-only, edit-layout and full-control levels, with approval prompts before any tool runs something on the user's computer.

An ultra-fast native MCP server for macOS desktop automation, enabling visual OCR, text-based clicking, window management, and keyboard/mouse control without hijacking the physical cursor.

Exposes two tools over stdio or HTTP that let AI agents read display geometry and capture full-screen, per-display, or region screenshots in PNG or JPEG. Runs as a VS Code extension or a standalone MCP server usable by Claude Code, Cursor, Cline and other clients.

Start, stop and read logs of your local dev servers from Claude Code, Cursor and Codex.

Enables ChatGPT, Claude, and Cursor to securely manage a VPS through filesystem operations, system monitoring, and long-horizon command execution, protected by OAuth 2.1 with PKCE.

Enables managing Ubuntu/Linux servers through natural language by establishing SSH connections and executing remote commands. Supports real-time command execution and output through Claude Desktop or Cursor IDE.

MCP server that enables AI agents to control Windows by clicking, typing, and navigating with a visible cursor overlay, using a layered approach (native UIA, browser CDP, pixel fallback) for reliable interaction.

An MCP server that allows AI tools like Claude Desktop, Claude Code, and Cursor to visually interact with macOS applications by capturing screenshots and controlling the mouse and keyboard.

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

MCP server for macOS disk cache management. Enables AI agents to free disk space on demand by scanning and clearing developer caches.

MCP server that lets Claude use your Mac — native apps and the browser — by remembering what it has seen instead of screenshotting every step.

Mac window manager AI agents can drive: see every monitor and window, apply multi-monitor layouts in one call, save and relaunch whole workspaces, snap zones, keep-awake, and annotated screenshots. Backed by a native macOS menu bar app over a local-only loopback API — no cloud, no telemetry.

Enables an agent to drive an Android phone attached via USB by reading the screen, deciding next steps, executing actions, and verifying results, all through adb.

Enables natural-language diagnosis of Linux system issues by providing sandboxed, typed tools for system, service, filesystem, and git inspection, with human approval for mutating actions.

Enables AI agents to query Windows process, window, and console information via structured JSON instead of screenshots, reducing token usage by 94-98%.

Inspect a cronstable job scheduler's jobs, logs, run history, DAG workflows, and cluster health, and ask why a job did or didn't run. Read-only by default; tools that run, pause, or approve jobs and workflow runs need opt-in.

Enables an AI agent to control a genuinely visible Windows terminal window by spawning it, sending keystrokes, reading the rendered console buffer, and closing it so a human can watch every action in real time.

jobd is a self-hostable, GPU-aware job broker that queues and routes shell commands across your own machines — picking workers by available VRAM and tool tags, streaming logs back, and surviving across sessions. It ships native MCP integration, so agents can submit, monitor, and control long-running or GPU jobs as tools.

Enables AI assistants to control Windows PCs by executing shell commands, managing files, capturing screenshots, and monitoring system information through a comprehensive set of MCP tools.

Enables MCP clients to start and control Owner-approved local POSIX subprocess sessions over stdio, with cursor-based output reads, input writes, status checks, termination, and resource/time limits.

Enables MCP-capable LLM clients to perform read-only Linux system observation and OS algorithm experiments by exposing typed tools for memory, filesystem, process, and CPU scheduling data with controlled, safe boundaries.