goose/documentation/docs/mcp/computer-controller-mcp.md
Angie Jones 9b6669a0b7
Some checks failed
CI / changes (push) Has been cancelled
Deploy Documentation / deploy (push) Has been cancelled
Live Provider Tests / check-fork (push) Has been cancelled
Publish Ask AI Bot Docker Image / docker (push) Has been cancelled
Scorecard supply-chain security / Scorecard analysis (push) Has been cancelled
CI / Check Rust Code Format (push) Has been cancelled
CI / Build and Test Rust Project (push) Has been cancelled
CI / Lint Rust Code (push) Has been cancelled
CI / Check OpenAPI Schema is Up-to-Date (push) Has been cancelled
CI / Test and Lint Electron Desktop App (push) Has been cancelled
Live Provider Tests / changes (push) Has been cancelled
Live Provider Tests / Build Binary (push) Has been cancelled
Live Provider Tests / Smoke Tests (push) Has been cancelled
Live Provider Tests / Smoke Tests (Code Execution) (push) Has been cancelled
Live Provider Tests / Compaction Tests (push) Has been cancelled
Live Provider Tests / goose server HTTP integration tests (push) Has been cancelled
docs: removing LLM Usage admonitions (#7227)
2026-02-14 17:38:56 +00:00

152 lines
No EOL
4.6 KiB
Markdown

---
title: Computer Controller Extension
description: Use Computer Controller MCP Server as a goose Extension
---
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
import YouTubeShortEmbed from '@site/src/components/YouTubeShortEmbed';
import GooseBuiltinInstaller from '@site/src/components/GooseBuiltinInstaller';
<YouTubeShortEmbed videoUrl="https://www.youtube.com/embed/EuMzToNOQtw" />
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
<Tabs groupId="interface">
<TabItem value="ui" label="goose Desktop" default>
<GooseBuiltinInstaller
extensionName="Computer Controller"
description="Automate everyday computer tasks and web interactions"
/>
</TabItem>
<TabItem value="cli" label="goose CLI">
1. Run the `configure` command:
```sh
goose configure
```
2. Choose to `Toggle Extensions`
```sh
┌ goose-configure
◇ What would you like to configure?
│ Toggle Extensions
◆ Enable extensions: (use "space" to toggle and "enter" to submit)
// highlight-start
│ ● computercontroller
// highlight-end
|
└ Extension settings updated successfully
```
</TabItem>
</Tabs>
## 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.
<Tabs groupId="interface">
<TabItem value="ui" label="goose Desktop" default>
1. Open a new session in goose Desktop
</TabItem>
<TabItem value="cli" label="goose CLI">
1. Open a terminal and start a new goose session:
```sh
goose session
```
</TabItem>
</Tabs>
### 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
```md
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](../assets/guides/computer-controller-csv-result.png)