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

Provides intelligent summarization capabilities through a clean, extensible architecture. Mainly built for solving AI agents issues on big repositories, where large files can eat up the context window.

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

Lets any number of concurrent Claude Code sessions drive a Firefox browser through the Browser Control extension by funneling every session's commands over a single shared port via a background daemon and private unix socket. Sessions no longer have to compete for a limited pool of extension ports, and requests stay isolated through per-request correlation ids.

Enables AI agents to drive a real headful Chrome browser using vision-first computer interactions, with support for multi-agent tab groups, password-manager-filled logins, and human handoff.

Enables AI agents to control monitor settings (brightness, contrast, input source) via DDC/CI protocol, with support for MQTT integration.

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.

A native MCP server that gives AI assistants full Chrome control via the DevTools Protocol and an unpacked extension, including semantic element refs, real input, screenshots, and browser/tab/window management. It exposes 43 callable tools with a visible control overlay and an optional read-only security profile.

An MCP server paired with a Firefox extension that enables LLM clients to control the user's browser, supporting tab management, history search, and content reading.

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.

Enables AI agents to control existing Chrome and Firefox browser sessions locally, including tab management, navigation, form filling, screenshots, and persistent scripts, without remote relays or debugging ports.

Publishes sample Python implementations that expose tools such as snippet CRUD, QR code generation and batch operations, resources, and prompts like code review checklists and doc generation, plus an interactive weather app, to MCP clients. These can be run locally with debugging or deployed to Azure with built-in Microsoft Entra authentication.

Enables developers to build and deploy custom tool, resource, and prompt integrations to the cloud using serverless functions, with local debugging and built-in authentication.

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 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.

Exposes the Codex Chrome extension flow to other Agent tools through MCP, enabling Chrome automation via CDP and tab management.

Operate the OpenClaw gateway's full management surface from any MCP client — list and trigger crons, inspect sessions, configure agents and channels, manage skills and secrets, pair devices, and more via 134 typed tools.

Enables MCP clients such as Claude to drive the user's real Chrome in the background via the DevTools Protocol through a companion extension, exposing 32 tools for navigation, form input, screenshots, snapshots, script evaluation, network and console inspection, performance tracing and raw CDP commands, with control off by default and limited by allowed sites and blocked domains.

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.

Enables AI agents to control Chromium-based browsers via CDP with 36 tools for navigation, input, screenshots, accessibility inspection, network monitoring, device emulation, and performance tracing.

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.

Enables local-first management of OpenCode model routing, letting users discover, enable, and assign orchestrator/specialist roles to models while safely connecting the chosen policy to OpenCode via a local MCP bridge.

Enables AI assistants to operate a real, logged-in Firefox session through an extension, including tab and history management, page reading, screenshots, and clicking, typing, or scrolling on domains the user approves.

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.

Turns any OpenAPI/Swagger specification into a functional MCP server, dynamically exposing API endpoints as LLM tools or generating standalone Python code.

Enables local/remote execution infrastructure through the official Codex Runtime, providing shell, files, Git, sessions, browser, computer use, recoverable tasks, multi-host routing, dynamic MCP integration, and skill lifecycle management.

Open-source, Windows-first control plane for operating local and homelab services through typed MCP servers, featuring 13 servers and 290 tools with infrastructure adapters for Windows, Ubuntu, Docker, and more.

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 durable, retry-safe automation of long-running Codex Desktop tasks through MCP, with async operations, polling, Plan Mode workflows, approvals, diagnostics, and restart recovery.

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.