- Home
- MCP servers
- Automator
Automator
- javascript
4
GitHub Stars
javascript
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"szowesgad-automator-mcp": {
"command": "automator-mcp",
"args": []
}
}
}This MCP server lets an AI assistant control macOS Automator actions and workflows, enabling you to automate tasks like scripting AppleScript, running JXA, and triggering predefined Automator quick actions from AI prompts. It expands what your Mac can do by integrating AI-driven commands with native macOS automation capabilities.
How to use
Connect an MCP client (such as Claude) to the Automator MCP server and start issuing commands that map to Automator actions and workflows. You can run AppleScript, execute JavaScript for Automation, trigger prebuilt quick actions, create new Automator workflows programmatically, and perform system automation tasks. Use natural prompts to describe the task you want to accomplish, and the server will translate it into the corresponding Automator actions on your Mac.
How to install
Prerequisites you need on your Mac before installing are Node.js and npm. If you don’t have them, install Node.js from the official site or via your preferred package manager.
Install the MCP server globally so you can run it from anywhere in your terminal.
npm install -g automator-mcp
Configure the MCP client to connect to this server by adding the following configuration in your client setup. This enables the client to reach the local server you start with the next step.
{
"mcpServers": {
"automator": {
"command": "automator-mcp"
}
}
}
Start the server using its CLI entry point. Run this in your terminal to begin listening for MCP clients.
automator-mcp
Configuration
You enable the server by defining an MCP server entry named automator with the local command. This is done on the client side to point requests at the locally running server.
{
"mcpServers": {
"automator": {
"command": "automator-mcp"
}
}
}
Examples
Examples of common tasks you can perform through the AI interface include creating and running Automator workflows, executing AppleScript or JXA, and triggering quick actions such as image resizing or PDF operations. These examples illustrate how you describe the task to the AI and how the server translates it into macOS automation.
Security and notes
When enabling AI-controlled automation on your Mac, consider privacy and security implications. Limit access to trusted AI clients and ensure your Mac is secured with appropriate user permissions and screen time policies. Regularly review the actions being triggered to avoid unintended automation.
Troubleshooting
If the server fails to start, verify you have Node.js and npm installed, and that the global npm bin directory is in your PATH. Check for any port or permission issues and ensure the client is configured to connect to the correct local command.
Notes
This MCP server exposes automation capabilities that integrate AI prompts with native macOS automation tools, enabling you to automate emails, file organization, workflow creation, and system tasks through natural language or structured prompts.
Available tools
run_applescript
Execute AppleScript code to control apps and automate tasks.
run_jxa
Execute JavaScript for Automation to automate macOS apps and workflows.
quick_action
Run predefined Automator quick actions for common tasks like image compression, PDF conversion, and more.
system_automation
Perform system-level actions such as emptying the trash, toggling dark mode, taking screenshots, or gathering system information.
create_workflow
Create new Automator workflows programmatically based on requested actions.
list_actions
List available Automator actions by category to discover automation options.