by dvcrn
This MCP server provides access to Siri shortcuts functionality via the Model Context Protocol (MCP). It allows listing, opening, and running shortcuts from the macOS Shortcuts app.
mcp-server-siri-shortcuts is an MCP (Model Context Protocol) server that enables Large Language Models (LLMs) to interact with Siri Shortcuts on macOS. It exposes all available Siri Shortcuts as MCP tools, allowing LLMs to list, open, and run them programmatically.
To use mcp-server-siri-shortcuts, you need to configure it within your LLM environment, such as Claude. The server can be run as a command-line process. You can configure environment variables like GENERATE_SHORTCUT_TOOLS
to control the generation of dynamic shortcut tools and INJECT_SHORTCUT_LIST
to inject the list of available shortcuts into the run_shortcut
tool description for better LLM understanding. An example configuration for Claude is provided in the README.
list_shortcuts
(to list all available Siri shortcuts), open_shortcut
(to open a shortcut in the Shortcuts app), and run_shortcut
(to run a shortcut with optional input parameters).run_shortcut_[sanitized_shortcut_name]
, enabling direct execution of specific shortcuts.shortcuts
CLI command for underlying functionality.Q: Can I disable the generation of dynamic shortcut tools?
A: Yes, you can set the GENERATE_SHORTCUT_TOOLS
environment variable to false
to disable the generation of dynamic shortcut tools. In this case, only the base tools (list_shortcuts
, open_shortcut
, run_shortcut
) will be available.
Q: How can I help the LLM understand which shortcuts are available?
A: You can set the INJECT_SHORTCUT_LIST
environment variable to true
. This will inject the list of available shortcuts into the run_shortcut
tool description, providing the LLM with more context.
Q: What kind of input can I pass to a shortcut?
A: You can pass either text input or a filepath as input to a shortcut when using the run_shortcut
tool.
Q: Does it work with all Siri Shortcuts? A: The server is designed to expose all shortcuts, meaning the LLM can call anything that is available in the Shortcuts app.
This MCP server provides access to Siri shortcuts functionality via the Model Context Protocol (MCP). It allows listing, opening, and running shortcuts from the macOS Shortcuts app.
list_shortcuts
{
"shortcuts": [{ "name": "My Shortcut 1" }, { "name": "My Shortcut 2" }]
}
open_shortcut
name
(string): Name of the shortcut to openrun_shortcut
name
(string): Name or identifier (UUID) of the shortcut to runinput
(string, optional): Text input or filepath to pass to the shortcutThe server automatically generates additional tools for each available shortcut in the format:
run_shortcut_[sanitized_shortcut_name]
input
(string, optional): Text input or filepath to pass to the shortcutThe server supports the following environment variables:
GENERATE_SHORTCUT_TOOLS
(default: true
): When set to false
, disables the generation of dynamic shortcut tools. Only the base tools (list_shortcuts
, open_shortcut
, run_shortcut
) will be available.INJECT_SHORTCUT_LIST
(default: false
): When set to true
, injects the list of available shortcuts into the run_shortcut
tool description to help the LLM understand which shortcuts are available.Add to your Claude configuration:
{
"mcpServers": {
"siri-shortcuts": {
"command": "npx",
"args": ["mcp-server-siri-shortcuts"],
"env": {
"GENERATE_SHORTCUT_TOOLS": "true",
"INJECT_SHORTCUT_LIST": "false"
}
}
}
}
shortcuts
CLI command under the hoodPlease log in to share your review and rating for this MCP.
Discover more MCP servers with similar functionality and use cases
by Skyvern-AI
Skyvern automates browser-based workflows using LLMs and computer vision, offering a robust solution for repetitive online tasks.
by PipedreamHQ
Connect APIs quickly, run event‑driven automations, and execute custom code in Node.js, Python, Go, or Bash on a hosted platform.
by czlonkowski
Provides AI assistants with structured access to n8n node documentation, properties, and operations, enabling automated workflow creation, validation, and management.
by executeautomation
mcp-playwright is a Model Context Protocol (MCP) server that enables large language models (LLMs) to perform browser automation and web scraping tasks using Playwright.
by browserbase
Provides cloud browser automation capabilities for LLMs, enabling web navigation, interaction, screenshot capture, and data extraction through Browserbase and Stagehand.
by haris-musa
excel-mcp-server is a Python-based Model Context Protocol (MCP) server that enables AI agents to programmatically create, read, and modify Excel files without requiring Microsoft Excel to be installed.
by mobile-next
Mobile-mcp is a Model Context Protocol (MCP) server designed for scalable mobile automation, app scraping, and development across iOS and Android devices, including physical devices, simulators, and emulators.
by anaisbetts
mcp-installer is an MCP server designed to automate the installation of other MCP servers, simplifying the process for users.
by leonardsellem
An MCP server that enables AI assistants to interact with n8n workflows through natural language.