Siri Shortcuts MCP Server
Enables interaction with macOS Siri Shortcuts via the Model Context Protocol, allowing users to list, open, and run shortcuts dynamically with optional inputs.
dvcrn
Tools
list_shortcuts
List all available Siri shortcuts
open_shortcut
Open a shortcut in the Shortcuts app
run_shortcut
Run a shortcut with optional input and output parameters
README
Siri Shortcuts MCP Server
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.

Features
- Exposes all shortcuts, meaning the LLM can call anything that is available in the Shortcuts app.
- List all available shortcuts
- Open shortcuts in the Shortcuts app
- Run shortcuts with optional input parameters
- Dynamically generated tools for each available shortcut
Tools
Base Tools
-
list_shortcuts- Lists all available Siri shortcuts on the system
- No input required
- Returns: Array of shortcut names
{ "shortcuts": [{ "name": "My Shortcut 1" }, { "name": "My Shortcut 2" }] } -
open_shortcut- Opens a shortcut in the Shortcuts app
- Input:
name(string): Name of the shortcut to open
-
run_shortcut- Runs a shortcut with optional input
- Input:
name(string): Name of the shortcut to runinput(string, optional): Text input or filepath to pass to the shortcut
Dynamic Tools
The server automatically generates additional tools for each available shortcut in the format:
- Tool name:
run_shortcut_[sanitized_shortcut_name] - Description: Runs the specific shortcut
- Input:
input(string, optional): Text input or filepath to pass to the shortcut
Usage with Claude
Add to your Claude configuration:
{
"mcpServers": {
"siri-shortcuts": {
"command": "npx",
"args": ["mcp-server-siri-shortcuts"]
}
}
}
Implementation Details
- Uses the macOS
shortcutsCLI command under the hood - Sanitizes shortcut names for tool naming compatibility
- Supports both direct text input and file-based input
- Returns shortcut output when available
- Implements standard MCP error handling
Recommended Servers
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Beamlit MCP Server
An MCP server implementation that enables seamless integration between Beamlit CLI and AI models using the Model Context Protocol standard.
ThingsPanel MCP
An integration server that connects AI models with ThingsPanel IoT platform, allowing AI assistants to interact with IoT devices through natural language for device control, data retrieval, and management operations.
JavaScript Sandbox MCP Server
Provides a secure, isolated JavaScript execution environment with configurable time and memory limits for safely running code from Claude.
aws-mcp
A Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with your AWS environment. This allows for natural language querying and management of your AWS resources during conversations. Think of better Amazon Q alternative.
MCP Server Make
A Model Context Protocol server that enables LLMs to safely execute make targets from a Makefile, allowing AI assistants to run tests, format code, and automate various development tasks through natural language interaction.
claude-code-mcp
This project aims to build a Claude Code MCP server and implement its associated tools (explain\_code, review\_code, fix\_code, edit\_code, test\_code, simulate\_command, your\_own\_query). The server is implemented using Node.js and the MCP SDK. It receives tool requests from clients via Stdio, dynamically
Super Windows CLI MCP Server
An enhanced Windows CLI MCP server providing unrestricted system access capabilities, designed for trusted environments with full system access requirements.
mcp-local-dev
Create sandboxed local development environments directly from Github and execute tests, see coverage and more! Supports Python, Node, Bun and many test runners.