Skip to content
Back to Tech
GenAI · 8 min read

My Favourite Claude MCPs for macOS

A living list of the Model Context Protocol servers I actually use every day on my Mac — what they do, why they earned a spot in my setup, and how to install each one in under five minutes.

The Model Context Protocol (MCP) is the part of the Claude ecosystem that quietly went from “neat extension mechanism” to “the reason I never close Claude”. Once you’ve wired Claude into the apps you actually live in — your notes, your mind maps, your mailbox, your browser — going back to a stock chatbot feels like coding without an IDE.

This post is a curated list of the MCP servers I genuinely use on macOS, day in, day out. It’s intentionally short. I’ll grow it over time as more keepers earn their place — but I’d rather recommend five things I use every day than thirty things I installed once and forgot.

For each one you’ll find: what it does, why I like it, and a copy-paste install recipe.

A Quick Note on How MCP Works on macOS

MCP servers are small local processes that Claude (Desktop, Code, or any MCP-aware client) launches on demand and talks to over stdio. On macOS that almost always means one of three runtimes:

  • Node.js (npx) — most common, zero install if you already have Node
  • Python (uvx from Astral’s uv) — increasingly the standard for Python servers
  • A native binary — rare, but a few servers ship as compiled tools

Claude Desktop reads its MCP configuration from:

~/Library/Application Support/Claude/claude_desktop_config.json

Claude Code reads from ~/.claude.json (or per-project .mcp.json), and you can also add servers interactively with:

claude mcp add <name> -- <command> [args...]

After editing config files you need to fully quit and relaunch Claude Desktop — a window close isn’t enough. For Claude Code, the next session picks up changes automatically.

If you don’t have the runtimes yet:

# Node (via Homebrew)
brew install node

# uv (for Python-based MCP servers)
brew install uv

That’s the entire prerequisites section. Onwards.

1. Obsidian MCP — Claude in My Second Brain

Repo: jacksteamdev/obsidian-mcp-tools

What it does: Gives Claude full read/write access to your Obsidian vault — searching notes, reading files, creating new ones, patching sections, executing Templater templates, even fetching the currently active file.

Why I love it: My vault is a decade of thinking compressed into markdown. Hooking Claude into it turned a passive archive into an active research partner. I can ask “what did I conclude about sleep cycles last year?” and get an answer grounded in my own writing, not a generic summary from the internet. Drafting new notes from a conversation is now a single sentence: “save this as a note in /Inbox with tags x, y, z” — done.

It also makes Claude shockingly good at synthesis across notes. Ask it to find tensions between two essays you wrote a year apart and it will actually do it.

Install:

  1. In Obsidian, install the Local REST API community plugin and enable it. Copy the API key it generates.
  2. Install the MCP Tools for Obsidian plugin (this ships the MCP binary itself). The plugin’s settings page has a one-click “Install MCP Server” button — let it do its thing. The binary will be placed inside your vault at .obsidian/plugins/mcp-tools/bin/mcp-server.
  3. Add to your claude_desktop_config.json:
{
  "mcpServers": {
    "obsidian": {
      "command": "/path/to/your/vault/.obsidian/plugins/mcp-tools/bin/mcp-server",
      "env": {
        "OBSIDIAN_API_KEY": "your-local-rest-api-key-here"
      }
    }
  }
}
  1. Quit and relaunch Claude Desktop. Ask it “list the files in my vault” to confirm it’s wired up.

Pro tip: Combine this with a Templater template that generates a daily note skeleton, then have Claude execute it each morning with today’s open tasks pulled from your project tracker.

2. XMind MCP — Mind Maps as a First-Class Output Format

Repo: apeyroux/mcp-xmind · npm: @41px/mcp-xmind

What it does: Lets Claude read, search, and create .xmind files directly. You can ask it to “turn this brainstorm into a mind map”, “extract the marketing branch from my product strategy map”, or “summarise everything under the ‘Risks’ node”.

Why I love it: Mind maps are the format I reach for when I’m thinking through anything with more than two layers of structure — product strategy, org design, conference talks, even debugging trees. Until this MCP existed, the loop was: think in Claude → manually rebuild as XMind. Now Claude just outputs an .xmind file and I open it. The friction collapse is unreasonable.

I also use it the other way around: feed Claude an existing map and ask it to critique the structure, find missing branches, or export a specific subtree as a markdown briefing for someone who doesn’t use XMind.

Install:

# The XMind MCP is a Node package — install via the Claude Code CLI
claude mcp add xmind -- npx -y @41px/mcp-xmind

Or for Claude Desktop, add to claude_desktop_config.json:

{
  "mcpServers": {
    "xmind": {
      "command": "npx",
      "args": ["-y", "@41px/mcp-xmind"],
      "env": {
        "XMIND_FILES_DIRECTORY": "/Users/YOUR_USERNAME/Documents/XMind"
      }
    }
  }
}

Set XMIND_FILES_DIRECTORY to wherever you keep your maps — the server scopes its file operations to that folder.

Pro tip: Pair it with the Obsidian MCP and ask Claude to “build an XMind from the headings of every note tagged #strategy in my vault”. Cross-tool composition is where MCP really shines.

3. GitHub MCP — The One I Forget I’m Using

Repo: github/github-mcp-server (GitHub’s official server)

What it does: GitHub’s official MCP server. Read and write issues, PRs, branches, file contents, run code search, manage releases, request Copilot reviews — basically the whole gh CLI surface, exposed as MCP tools.

Why I love it: Every “go check what’s happening on PR 412” or “open an issue describing this bug” used to mean a context switch. Now it’s a sentence in the same conversation where I just diagnosed the problem. For maintainers of multiple repos this is the single biggest time saver in my whole MCP stack.

Install:

claude mcp add github -- npx -y @modelcontextprotocol/server-github

You’ll need a GitHub Personal Access Token with repo scope. Either export it as GITHUB_PERSONAL_ACCESS_TOKEN in your shell, or pass it inline in claude_desktop_config.json:

{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_xxx..."
      }
    }
  }
}

4. Apple Mail MCP — Inbox Triage Without Leaving Claude

Repo: patrickfreyer/apple-mail-mcp

What it does: Drives Apple Mail via AppleScript. Search messages, read threads, draft replies, archive, move between mailboxes, get an “inbox dashboard” overview, list emails awaiting reply.

Why I love it: I deliberately keep my mail in Apple Mail rather than a webmail UI because I want it local, fast, and scriptable. This MCP makes “scriptable” actually mean something. The killer workflow: every morning I ask Claude for an inbox_dashboard summary, it tells me what genuinely needs a response, drafts replies for the obvious ones, and archives the noise. Inbox zero in five minutes.

Because it’s AppleScript-based, everything happens locally — no IMAP, no third party, no credentials in a config file.

Install: Requires uv (brew install uv). Then:

claude mcp add apple-mail -- uvx apple-mail-mcp

The first run will trigger a macOS automation permissions prompt — grant Claude (or your terminal app, depending on how you launched it) access to control Mail. If you miss the prompt, you can grant it manually under System Settings → Privacy & Security → Automation.

5. Claude Preview MCP — A Real Browser for the Agent

Bundled with Claude Code — no separate repository, ships with the official CLI from Anthropic.

What it does: Spins up a controllable browser/dev-server preview that Claude can actually look at — start servers, click buttons, fill forms, take screenshots, read console logs and network traffic, inspect computed CSS.

Why I love it: This is the MCP that makes Claude Code genuinely capable of frontend work. Instead of editing a component and asking me “can you check if it looks right?”, it edits, reloads, takes a screenshot, sees the broken layout, fixes it, and shows me the working result. The verification loop is closed inside the agent — which is exactly what you want from an autonomous coding session.

It has fully replaced the “Claude in Chrome” extension in my workflow for anything dev-server related.

Install: Bundled with recent Claude Code releases — check claude mcp list to confirm Claude_Preview is present. If not:

claude mcp add claude-preview -- npx -y @anthropic-ai/claude-preview-mcp

No environment variables needed. Test it by asking Claude to “start a preview server in this project and screenshot the homepage”.

What’s Next

This list is intentionally a starting point, not a finished taxonomy. The MCPs I’m currently evaluating for inclusion in version 2 of this post:

  • Linear MCP — for the bits of project management that don’t live in GitHub
  • Spotify MCP — half novelty, half “actually useful for building focus playlists from a conversation”
  • Figma MCP — translating designs into code with real component awareness
  • Scheduled Tasks MCP — for turning ad-hoc Claude workflows into recurring agents

I’ll add them here once they’ve earned a spot through actual daily use, not just installation. The bar I hold MCPs to is simple: if I uninstalled it tomorrow, would I notice within a week? Everything above passes that test.

If you have a Mac MCP I should be trying, tell me on LinkedIn — I’m always looking.

claude mcp macos claude-code claude-desktop xmind obsidian productivity