"How to control macOS settings or functions" matching MCP servers:

Give AI agents eyes and hands on macOS.

Enables AI agents to control macOS desktop applications through screenshot capture, accessibility/OCR perception, virtual cursor input injection, semantic actions, and self-healing SOPs.

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.

MCP server that gives Claude Code full mouse, keyboard, and app control on macOS. Tell Claude what to do and watch it operate your computer.

Enables Claude Code to read and operate macOS app interfaces through the accessibility tree, pressing buttons, setting text fields, typing with IME support, sending shortcuts, scrolling, dragging, and capturing screenshots. It drives background apps without moving the mouse or stealing focus from the user's current work.

Enables AI to remotely control macOS systems via VNC with full desktop capabilities including screenshots, mouse control, keyboard input, and application management. Includes a web-based chat interface for natural language control.

The first open-source MCP server that enables AI to fully control remote macOS systems.

Enables a macOS MCP client to control a real iPhone through CoreDevice services, including screenshots, normalized taps and swipes, text entry, hardware-button presses, and app launching or listing.

A governance and control layer for MCP tools that manages tool requests as intents through policy-based approval, queuing, or blocking. It enables secure human oversight and audit trails for consequential agent actions across platforms like Claude Desktop and Cursor.

Enables LLMs to orchestrate AI agents and tasks, inspect DAG workflows, monitor cluster metrics, and perform safe database queries and statements through standardized MCP tools.

Enables users to deploy a production-grade control plane for agents, providing a spec-compliant MCP server, scoped tool grants, failure-mode detection, and cost governance.

Enables MCP-capable agents to control the macOS mouse and keyboard using screenshots and Quartz-based input events, including app switching, clicks, scrolling, text entry, shortcuts, and action-triggered screenshots.

Enables coding agents to request, track, and verify independent cross-model reviews with structured findings, attachment hashes, and provenance receipts via Chrome Bridge, Codex, or Responses transports.

Enables one coding agent to inspect, configure, debug, and repair another agent over stdio MCP, with redacted reads and confirm-gated writes and restarts.

Enables reviewing and dispatching existing Codex tasks across projects through a lightweight control panel, including scanning task inventories, confirming Continue or Optimize prompts, and tracking dispatch progress.

Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, retrieve skill details and content, and read supporting files with security protections.

Start, observe, and interact with Claude Managed Agents from any MCP client — launch an agent, watch its events, reply, approve the tools it wants to run, and stop it. Runs over stdio, HTTP, or AWS Lambda with pluggable auth.

Enables AI agents to observe and operate a real Windows or Linux desktop like a human — snapshotting screen geometry, active window, OCR text and normalized UI elements, then clicking, typing, scrolling and managing windows with built-in verification and recovery. Backends are chosen automatically per action (UIA/AT-SPI → OCR → vision → PyAutoGUI), so browsers, IDEs, office suites and canvas apps are all controllable without any browser-automation MCP.

This server enables AI agents to operate Windows and Linux computers by observing the screen, understanding the UI through accessibility, OCR, and vision, and performing mouse, keyboard, window, clipboard, and system actions with verification and recovery.

A Model Context Protocol server that converts Markdown content to HTML format.

Enables AI assistants to observe, reason about, and control connected Android devices via ADB, providing tools for screenshots, UI hierarchy parsing, semantic element clicking, gestures, text input, and app lifecycle management.

Enables Claude to use Google Gemini as a secondary AI through MCP for large-scale codebase analysis and complex reasoning tasks. Supports both Gemini Flash and Pro models with specialized functions for general queries and comprehensive code analysis.

Enables safe automation of Chrome browser through a local MCP server and Chrome extension, allowing LLMs to control browser tabs, pages, and computer-use actions with permission controls.

AI-native orchestration layer with 80+ tools for task management, code editing, browser automation, terminal control, and persistent memory across CLI, local MCP, and cloud deployments.

Enables MCP clients to interact with A2A agents through four ordinary tools, translating agent discovery, messaging, task reading, and cancellation between the A2A and MCP protocols, with support for the tasks extension.

A basic example of developing and running serverless Model Context Protocol (MCP) using Netlify Functions, demonstrating how to deploy and access serverless functions with customized URLs.

An MCP server that turns a one-sentence idea into working, tested code using a pipeline of six AI agents, with optional deployment.

Enables MCP clients such as Claude Desktop to hand tasks to a running DeepSeek Harness window, where each task becomes a real session visible in the sidebar with a reusable session id. If the in-process plugin is unavailable, it falls back to running the task headless so the tool still returns a result.

Serves a loopback-only MCP endpoint that lets a same-machine client start, steer, and cancel DSH Sessions it knows by id, list their durable subagent trees, deliver messages to continuable children, and read durable event logs with paging and chunked oversized-event recovery. It maps every call onto native Session Controller and subagent services without owning task state, starting a second listener, or registering model-facing tools.

Enables persistent terminal sessions across multiple shells (Bash, CMD, PowerShell, WSL) with incremental output reading and autonomous goal execution with acceptance criteria.

Enhanced MCP server for full computer control: mouse, keyboard, screenshots, OCR, deep UI automation, semantic element actions, process management, filesystem watching, and accessibility-aware app launching.

Enables MCP clients to submit long-running Codex Desktop tasks as durable asynchronous operations, poll their status, handle approvals and Plan Mode workflows, and retrieve final reports without holding calls open. It also provides retry-safe submission, restart recovery, queue and worker status, diagnostics, and repair for local Codex automation.

Enables MCP clients to drive Codex Desktop and codex-app-server through durable asynchronous operations for long-running tasks, with polling, approvals, Plan Mode workflows, retry-safe submission, and structured final reports.

Enables MCP clients to drive Codex Desktop and codex-app-server as a durable asynchronous worker for long-running tasks, with polling, approvals, Plan Mode workflows, retry safety, diagnostics, and final reporting. It also provides recovery, queueing, and repair tools for reliable local automation.

Enables MCP clients to submit and manage long-running Codex Desktop work asynchronously, with durable operation/workflow IDs, polling, approvals, Plan Mode workflows, retry safety, diagnostics, and final reports.

Enables MCP clients to drive Codex Desktop as a durable async worker, submitting long-running tasks or Plan Mode workflows and polling for status, approvals, and final reports without holding multi-hour calls open. Adds retry-safe submission, duplicate prompt protection, restart recovery, and local SQLite state for reliable orchestration.

Enables MCP clients to drive Codex Desktop as a durable async worker: submit a task or Plan Mode workflow, immediately receive an operationId or workflowId, poll status, answer approvals, and read the final report. It also handles app-server startup, retry-safe duplicate prompt protection, persisted state and diagnostics so long-running Codex work survives client timeouts and restarts.

Enables MCP clients and local orchestrators to submit long-running Codex Desktop tasks asynchronously, poll durable operation or workflow status, handle approvals and Plan Mode, and retrieve final reports with retry-safe recovery and diagnostics.

Enables MCP clients to submit and manage long-running Codex Desktop tasks through durable asynchronous operations, polling, approvals, Plan Mode workflows, and final reports.

Enables MCP clients and orchestrators to submit long-running Codex Desktop tasks, poll their status, handle approvals and Plan Mode workflows, and retrieve final reports with diagnostics and recovery.