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

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 inspecting and managing a Cloudflare account from MCP-compatible clients, with OAuth/PKCE support and a read-only mode for ChatGPT, plus a legacy bearer-token path for full tool access.

Enables AI agents to safely read, audit, and manage Clash Verge Rev / Mihomo configuration with read-only and controlled runtime operations.

Exposes any stdio-based MCP server over the MCP Streamable HTTP transport so remote clients can reach it, spawning an isolated child process per session and gating access behind a secret URL path.

Enables AI agents and MCP clients to audit, monitor, diagnose, and safely manage Grandstream UCM phone systems, including extension status, call reports, site reconciliation, and confirmed test calls or admin edits.

Enables AI assistants to manage Cloudflare infrastructure including DNS records, cache purging, SSL settings, Workers, and analytics through the Cloudflare API. Eliminates dashboard context-switching by allowing natural language control of domain management and infrastructure operations.

Enables LLMs to configure Tencent Cloud resources such as DNSPod DNS records and CVM/Lighthouse security group rules by controlling a locally logged-in Edge browser over CDP, leveraging existing login state without needing API keys or credentials.

A governed MCP server that enforces OAuth 2.1 scope checking and policy-driven access control for AI agents, providing a full audit trail on every tool call. It includes tools for Cisco Webex Contact Center knowledge search and SD-WAN network operations.

MCP server with tools for managing routers, enabling network control through natural language.

Enables AI assistants to bulk-check hundreds of brainstormed domain names in a single call, reporting which are available, taken, or reserved along with buy links and prices from multiple registrars. It runs locally via DNS, RDAP, and WHOIS lookups, with optional registrar API keys for confirming availability and premium pricing.

Gives AI agents access to public internet interconnection data, letting them look up which networks connect to each other, at which internet exchanges and facilities they are present, under what peering policy, and who a given IP range or AS number is registered to. Responses are compact, sourced and aged, and it distinguishes missing records from genuinely absent networks rather than guessing.

Enables an LLM to read and write NetBox data through its REST API, supporting listing endpoints, inspecting schemas, and creating, updating, or deleting objects.

Uptime monitoring for websites, APIs, SSL certificates, domain expiry, ping and TCP/UDP ports. 15 tools to list, create, pause and delete monitors, pull incident timelines with error codes, and read hourly or daily uptime and response-time statistics.

Enables agents to run SEO and AI-search readiness audits (llms.txt, crawler access, sitemaps, structured data, redirects, indexability, and more), look up startup revenue listings and leaderboards, and check a domain's SPF, DKIM, DMARC, and MX records with concrete fixes. Runs locally over stdio with no account or API key, and frames all third-party responses as untrusted data.

Enables AI apps to inspect and manage a NextDNS account in plain language — profiles, analytics, query logs, blocklists, security and parental control settings — with every change saved and reversible via undo. It runs self-hosted on your own computer or server, keeps per-profile read/write/hidden permissions, and requires double confirmation for deletions or overwrites.

Enables LLM agents to read 3x-ui panel data and perform full CRUD operations on inbounds and clients.

Enables AI assistants to view devices on a Portveil account and move, rotate, reconnect, or disconnect them across VPN locations, with verified successful moves.

Enables looking up registration details for domains, URLs, or email addresses, returning registrar, creation and expiry dates, domain age, status codes, nameservers, DNSSEC, and registrant organization and country per domain. Queries registries directly via RDAP or WHOIS with no API key, running on Apify.

Enables unified administrative control over Cloudflare, Porkbun, Docker, Proxmox VE, Nginx Proxy Manager/NPMPlus, Uptime Kuma, Authentik, and Coolify. Exposes service discovery and action execution through three MCP tools with roughly 150 cataloged operations for managing DNS, containers, VMs, proxies, monitors, users, and related infrastructure.

Enables MCP-capable AI clients to inspect live lab topology, manage terminal sessions, run commands, collect evidence, and support network investigation, troubleshooting, and validation while engineers retain control over managed definitions and decisions.

Enables AI agents to perform compensating-control lifecycle operations on Check Point firewalls, including adding access rules, publishing sessions, and installing policies.

MCP server to manage and inspect a ZTE ZXHN F680 GPON router, enabling conversational control of NAT/port forwarding and reading WiFi, DHCP, DMZ, WAN, and device status from MCP-compatible clients.

Diagnoses a domain's email authentication — SPF, DMARC, DKIM, MX, blacklists and domain or SSL expiry - and returns copy-paste fix records generated by a validating engine, never a language model. The MCP server is hosted remotely; this repository carries the plugin manifest, connector config and bundled skill.

Enables agents to discover, rank, live-test, and cache free HTTP/HTTPS/SOCKS proxies, optionally filtered by country or protocol, returning the fastest working proxy and backups for routing requests through specific regions.

An MCP server that gives an AI agent safe, high-level control over Namecheap domains – availability checks, registration, DNS, email forwarding, transfers, WhoisGuard privacy, and account balance via Namecheap's XML API. Designed for safe LLM interaction with built-in confirmation gates and read-modify-write DNS operations.

Enables AI agents to classify IP addresses through the VPNDetection API with read-only tools that detect VPNs, residential and datacenter proxies, Tor nodes, relays, hosting providers and CDNs, in single or bulk lookups of up to 100 addresses. It also exposes which datasets an organisation is licensed for, along with their metadata and published checksums.

Enables MCP-speaking agents to claim and manage free subdomains under makes.fyi or agentdomains.co, including DNS records, HTTPS, URL forwarding, reverse proxying, and account management.

Enables managing GoDaddy domains through MCP, including domain listing, DNS record administration, availability and pricing checks, and domain registration or renewal from any MCP client.

Enables AI agents to query Oracle WebLogic Server runtime state, health, and JVM metrics through the REST management API, and to start, shut down, or force-shut-down servers via Node Manager, all under a least-privilege account with allowlisting, read-only mode, and JSON audit logging for every call.

A modular MCP server for analyzing PCAP files using protocol-specific analysis tools, enabling LLMs to read and analyze network packet captures from local paths or remote URLs.

Enables coding agents to inspect and change Cloudflare zones, DNS, settings, analytics, Workers, Pages, storage, tunnels, and Email Routing. Read tools run without prompting, while write tools are gated by the host's permission rules.

Exposes FFraud's fraud-detection tools so assistants can score a website's security, rate any IP for fraud and VPN/proxy/Tor use, and flag disposable emails, throwaway-mailbox domains, and community IP reports. It runs as a remote MCP endpoint or locally over stdio with no API key required.

Converts plain-language storage requests into validated Hitachi raidcom command lines and multi-step shell scripts, including ready-made provisioning recipes, command lookup, and model limit checks. It is build-only: it never connects to a storage system, runs a command, or holds credentials, returning reviewed command text for a person to execute.

Enables Claude Desktop to control serial-port devices like network craft ports, radios, rotators, and microcontrollers by sending commands and reading responses until a prompt or available output.

Comprehensive MCP server for the Namecheap API, enabling domain management, DNS record control, nameserver settings, and domain registration from any MCP client.

Enables MCP clients to scan nearby Wi-Fi networks with signal strength, channel, band and security details, inspect the current connection, and analyze channel congestion to recommend the best router channel while flagging open or weakly secured networks. Runs fully locally and read-only with zero dependencies across macOS, Windows and Linux.

Enables LLM clients to inspect and manage a TP-Link Deco mesh Wi-Fi network, covering mesh nodes, connected devices, SSIDs and radio settings, internet status, blocked clients, and DHCP address reservations. Runs entirely against the router on the local network without any cloud account.

A read-only MCP server that lets an AI agent inspect a ROS2 graph, its underlying DDS participants, readers, writers and QoS mismatches, and recorded bag files, with twelve typed tools that behave the same against a live robot or built-in mock fixtures. It has no write path at all, so it can never publish to the bus or command a robot.

Enables managing a self-hosted Headscale control server through its HTTP API, covering users, nodes, pre-auth and API keys, auth, policy, and metadata with write previews and confirmations.

Enables coding agents to perform network diagnostics and lookups, including subnet calculations, port and MAC vendor information, DNS and blocklist checks, TLS certificate inspection, and public IP discovery, all without needing an account or sending telemetry.