Skip to content

How to Connect Goose to Your Mac Apps with MCP

In short: Connect Goose to 201+ local LMCP tools for Mac apps. Your selected cloud AI provider can receive requested results.

L
LMCP··2 min read

Average 5.0 out of 5 · Ratings: 2See all reviews →

  • “The no-tokens part is huge. Setting up Graph API and dealing with auth flows is what usually kills these setups for me before I even start.”

    Lisa S.
  • “This is AMAZING! My daily work can all be managed from my key apps now. The OmniFocus integration was the missing piece.”

    Steve H.

How LMCP sets up Goose — Mac: Automatically (installer and menu) — Restart the app · Windows: From the app's own MCP settings

What this lets you do

Goose is Block’s open-source, on-machine AI agent. It talks to MCP servers as “extensions.” Add LMCP and Goose can act on the apps on your Mac — read your email, check your calendar, search Teams — through local tools. Your selected cloud AI provider can receive requested results.

Step 1: Install LMCP

In any terminal (macOS 13+):

curl -fsSL 'https://local-mcp.com/install?ref=guide-goose-mac' | bash

Or download the app. LMCP starts in your menu bar.

Step 2: Add LMCP as a Goose extension

Easiest — the CLI: run goose configure, choose Add Extension → Command-line Extension, then:

  • Name: local-mcp
  • Command: npx -y local-mcp@latest
  • Timeout: 300

Or edit the config file at ~/.config/goose/config.yaml:

extensions:
  local-mcp:
    type: stdio
    cmd: npx
    args: ["-y", "local-mcp@latest"]
    timeout: 300

(Goose uses npx to launch it, so you need Node.js installed.)

Step 3: Try it

Start a Goose session and ask:

List my email accounts

Goose calls the tool on your Mac and returns the result.

Troubleshooting

The extension won’t start — make sure the Local MCP app is running (menu-bar icon) and npx is on your PATH.

Timeouts — a first run downloads the package; keep the extension timeout at 300s.

Ready to try it?

Works with Claude, Cursor, VS Code, ChatGPT and any MCP client

Download for Mac
macOS 13+ · Apple Silicon & Intel

✦ llms.txt

Comments

Questions and experiences welcome — comments are reviewed before they appear.