Skip to main content

Computer Controller Extension

The Computer Controller extension helps automate everyday computer tasks and web interactions such as searching the web, controlling system settings, processing data files, and controlling applications without needing to know how to code.

This tutorial covers enabling and using the Computer Controller MCP Server, which is a built-in Goose extension.

tip

Let Goose complete its tasks without interruption - avoid using your mouse or keyboard until it's done.

Configuration​

  1. Ensure extension is enabled:
  1. Run the configure command:
goose configure
  1. Choose to add a Built-in Extension
┌   goose-configure 
│
◇  What would you like to configure?
│  Add Extension 
│
◆  What type of extension would you like to add?
│  ● Built-in Extension (Use an extension that comes with Goose)
│  ○ Command-line Extension 
│  ○ Remote Extension 
└
  1. Select the Computer Controller extension
┌   goose-configure 
│
◇  What would you like to configure?
│  Add Extension 
│
◇  What type of extension would you like to add?
│  Built-in Extension 
│
◆  Which built-in extension would you like to enable?
│  ○ Developer Tools 
│  ● Computer Controller 
│  ○ Memory 
|  ○ JetBrains
└  Enabled Computer Controller extension

Example Usage​

In this example, I'll show you how Goose can multitask, handling everything from system controls and music playback to web research and data organization.

LLM

Anthropic's Claude 3.5 Sonnet was used for this task.

  1. Open a terminal and start a new Goose session:
goose session

Goose Prompt​

Goose, I need to decompress while researching AI models for tomorrow's meeting. Can you create a relaxing environment and help me research?

1. Play classical music in Safari
2. Dim screen brightness (2 levels)
3. Research current flagship AI models (Anthropic, OpenAI, Google):
    * Verify availability
    * Collect: release date, features, pricing, context window
    * Use official sources only
4. Create "ai-models-comparison.csv" on desktop with collected data
5. Launch Numbers and open the CSV file
6. Reset brightness and close Safari

Goose Output​

I'll help you create a relaxing research environment and gather information about AI models. I'll break this down into steps:

1. First, let's set up the relaxing environment with classical music and dimmed screen:

─── computer_control | computercontroller ──────────────────────────
script: ...



2. Now, let's research the AI models. I'll use web search and scraping to gather
 information from official sources:

─── web_search | computercontroller ──────────────────────────
query: Claude




─── web_search | computercontroller ──────────────────────────
query: GPT4




─── web_search | computercontroller ──────────────────────────
query: Gemini



3. Let's create the CSV file with the collected information:

─── automation_script | computercontroller ──────────────────────────
language: shell
script: ...



4. Now, let's open the CSV file in Numbers and reset the environment:

─── computer_control | computercontroller ──────────────────────────
script: ...

I've completed all the requested tasks:
1. ✅ Played classical music in Safari
2. ✅ Dimmed screen brightness
3. ✅ Researched current flagship AI models
4. ✅ Created the CSV file on desktop
5. ✅ Launched Numbers and opened the CSV file
6. ✅ Reset brightness and closed Safari

The CSV file has been created on your desktop with the following information for each model:
- Model name
- Company
- Release date
- Key features
- Context window size
- Pricing information

The file is now open in Numbers for your review. The environment has been reset to normal settings. Is there anything specific about any of the models you'd like me to elaborate on?

Results​

Computer Controller MCP Output