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

Enables an AI agent to safely observe and operate a Mac, starting read-only with optional read-write and admin tools for files, processes, apps, shell, AppleScript, and GUI control behind explicit permissions and human approval.

Local OCR & image analysis via Apple Vision Framework — private, offline, no API keys. Extracts text from images and PDFs, detects faces, barcodes, QR codes, and document corners. Works with Claude Code, Claude Desktop, and Cursor.

Let AI agents operate a real USB-connected iPhone from Linux — no Mac, no jailbreak, no paid developer account. Screenshots, taps, swipes, text input, element tree and app control via WebDriverAgent, with CoreDevice HID fallback.

Deterministic, LLM-first control of Word documents (.docx). An agent reads the outline, finds text by phrase, and applies edits as tracked changes and comments in one atomic batch, with a safety layer that refuses edits based on a stale read and rolls back failed batches. It works on .docx files directly, and can also drive an open document in Microsoft Word on Windows or in LibreOffice Writer.

One local MCP server for Mail, Calendar, Reminders, Notes, Messages and five more macOS apps. Searches return pointers, not full bodies; deletes, moves and sends preview first; sending is off by default.

Enables agents to convert Markdown into WhatsApp-compatible formatting, including styled text, lists, and tables that fit a phone's monospace width.

Enables MCP clients to turn Make blueprints and Zapier exports into n8n workflow files, with a per-step report of what converted, what to review, and what must be finished by hand. Also lists zaps, explains how individual steps are handled, checks workflow files for broken links or placeholders, and can upload the result to an n8n instance as an inactive workflow.

Enables AI assistants to convert CSS-animated SVGs into videos (MP4/WebM/MKV/MOV) and animated images (aPNG/GIF) with frame-accurate rendering and transparency support.

Provides full control of a macOS system, enabling AI agents to execute shell commands, run AppleScript, manage files and processes, and perform human-like GUI interactions such as clicking, dragging, scrolling, and typing, with a screenshot-based perception loop.

Enables AI agents to drive the Arc browser on macOS, including tab management, navigation, page reading, DOM interaction, and JavaScript scripting via AppleScript automation.

Enables AI agents to control the user's Chrome or Firefox browser, leveraging existing sessions for tasks requiring authentication and user handoff.

Deterministic Markdown-to-Word (.docx) publishing compiler with native OMML equations, three-line tables, CSL citations, and quality gates for AI agents.

A runtime-free MCP server that converts source code into AST🌲, regardless of language.

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.

Enables AI agents to control hardware devices like Arduino, Raspberry Pi, 3D printers, CNC machines, and custom robots via serial ports and HTTP. Provides tools for device discovery, command sending, sensor reading, servo control, G-code execution, and emergency stops with safety features.

Lets AI agents turn a repository's git history into proposed GitHub issues grouped into units of work, each with a commit checklist and links, then create and close them only after approval. Planning is read-only and creation defaults to a dry run, skipping anything that already exists.

MCP server that converts web page URLs to Markdown via the Zyla API.

Generates quality control plans and inspection reports from technical-drawing PDFs: tolerances, fits, threads, GD&T and surface finishes are extracted automatically by Imnoo's drawing analysis, numbered as balloons with acceptance limits and measuring instruments, and exported as a ballooned drawing PDF, an inspection package and an Excel measurement report.

Enables AI assistants to convert recipe amounts between volume and weight for specific ingredients using measured densities, scale recipes, and convert oven temperatures, with source citations and alternative published values.

Text-to-speech MCP server that enables AI assistants to read text aloud on the user's computer using Windows SAPI, with no API key or cloud service required.

Enables AI assistants to look up US census tract, block group, block, county FIPS, and legislative districts from a street address or latitude/longitude via the Census Geocoder, and to decode census GEOIDs offline.

Enables any AI agent to perceive and control a Windows desktop through live screen capture, OCR, and safety-gated mouse/keyboard actions via a local HTTP API and MCP.

Enables AI assistants to convert raw and cooked weights for meat and poultry by cut and cooking method from USDA data, calculate how much raw meat to buy for cooked servings, and look up cooking yields and sample ranges.

MCP server that routes Claude Desktop chat into Claude Code, enabling headless execution and terminal handoff with session continuity.

Enables centrally authoring and validating reusable agent guidance and delivering it across MCP-compatible hosts via registry resources, prompt templates, skill execution, and shared state.

Enables AI agents to see and operate a real USB-connected iPhone from a Linux Docker host — taking screenshots with region zoom, reading the element tree, tapping, swiping, long-pressing, typing text, pressing hardware buttons, listing/launching/terminating apps, and opening URLs. Automatically recovers from replugs and crashes, re-signs its automation agent before expiry, and falls back to a signing-free HID path on newer iOS.

Enables pushing enriched leads into Instantly or Smartlead campaigns with ICP score gating, deduplication, and dry-run previews via an Apify actor.

Resolves a company domain to its LinkedIn company page URL. Lightweight enrichment tool for sales and prospecting workflows.

Enables resolving the likely employer behind Gmail, Outlook, iCloud, Yahoo, and other free-mail signups by checking public Gravatar profiles, signed GitHub commits, and LinkedIn results. It returns the person’s name, employer, employer domain, confidence score, and evidence URLs.

Enables detection of AI-generated content in images, videos, audio, and text via the AI or Not API. Supports media analysis tools for deepfakes, synthetic voices, and AI-written text.

Enables converting Markdown and HTML tables into structured JSON records with automatic column type inference and format normalization. It also offers supporting web-agent primitives such as DOM semantic pruning, form field auto-mapping, and execution trajectory evaluation, all via a zero-dependency MCP server.

Enables agents to break high-level business objectives into dependency-ordered sub-task graphs and then directly generate the finished deliverables, such as financial spreadsheets, executive presentations, and analytical reports. It runs as a zero-dependency Python MCP server over JSON-RPC stdio, adding deterministic authorization, role-boundary validation, and telemetry.

Enables clients to look up dress-code meanings, generate five-piece outfit formulas for an occasion and weather, explore tested clothing colour combinations, and find relevant style guides through a free read-only MCP endpoint.

Web search, crawling and ranking evaluation on your own YaCy peer: no API key, no central service. Results carry author-signature verdicts and declared tags.

Enables lookup of licensed US real estate agents on official state license registers by license number or name, returning the brokerage of record along with its active agent count, size band, and the agent's license status and expiry. It also lists every active agent at a given brokerage or every brokerage office in a zip code across 19 states.

The pixel-diff verifier for Figma-to-code: converts a frame to HTML, React, Next.js or Tailwind with design tokens, then renders it and pixel-diffs it against Figma until it converges. Also verifies your own running app.

Publishes what an AI made — a page, a markdown or PDF doc, or a whole site — to a live HTTPS link. Runs locally over stdio from the @drop2run/mcp npm package, or hosted at https://mcp.dropto.run/mcp for chats that connect by URL.

Free JSON Schema validation, JSON to TypeScript, CSV to JSON, JSON repair and JSON to CSV for AI agents. Hosted MCP plus local STDIO. Connect once with a scoped key; enforce tool allowlists and quotas, inspect request IDs. Runnable repair → validate → CSV workflow. Bounded OpenAPI and webhook checks. No LLM calls or payments. Setup: invokeport.com/agents.

TO DO microsoft

agentcentral is a hosted MCP server for Amazon sellers that connects Claude, ChatGPT, and other AI clients to Amazon Ads, Seller Central, inventory, orders, catalog, rankings, finance, and fulfillment data. It provides fast reads from pre-materialized Amazon data, scoped API keys, OAuth-based Amazon connections, encrypted tokens, per-tenant isolation, and guarded write tools with audit log