1. Workshop setup
3m

Overview

In this beginner-friendly session, you'll get hands-on with the Model Context Protocol (MCP) and Apollo's MCP Server to enable assistants like Claude or ChatGPT to safely interact with your internal systems. Learn how to expose secure, task-specific tools that let your assistant operate independently while you stay in control.

What you'll do

  • Generate a from REST API endpoints using MCP tools and Goose
  • Set up Apollo MCP Server to connect AI assistants to your backend services
  • Build MCP tools easily with s
  • Test AI assistants executing real actions through connected tools

Who this workshop is for:

  • Developers and teams looking to integrate AI agents into real workflows.

Pre-requisites:

  • Basic experience with APIs and AI Agents.

⚠️ Important note

This workshop companion is designed to be used alongside an instructor for the Torc Community. If you would like to learn on your own time at your own pace, check out the Odyssey courses about MCP and Connectors instead.

Let's get set up!

  • Clone and configure the repository
  • Download and configure Goose CLI
  • Configure tools and in Goose
  • Install the

Clone the repository

In your terminal, run the following command to clone the repository.

git clone https://github.com/AmandaApollo/torc-mcp-workshop.git

Open it up in your favorite code editor.

Task!

Generate your OpenWeather key

The Open Weather API provides free access to its current weather API. To generate an API key, you must sign up for an account.

  1. Navigate to the signup page and fill out the form.

  2. You will be prompted to state your use of the API. You can choose education or other for purpose.

  3. Confirm your email.

  4. Click the dropdown second from the right in the top navigation > select My API keys.

  5. Copy the generated default key here and add it to your .env file as OPEN_WEATHER_KEY.

    .env
    OPEN_WEATHER_KEY=<YOUR_OPEN_WEATHER_KEY>

    Screenshot open weather api key dashboard

Task!

Download and configure Goose CLI with OpenRouter

We'll be using Goose CLI as our AI agent for development of your .

Follow the Installations guide on Block's official website. You'll either install via download script or via Homebrew.

If you already have Goose installed, run goose update.

Tip: When goose prompts you to enter your password after installation and on running, make sure to check Always Allow.

Task!

Provider Note

This workshop was designed using claude-sonnet-4 as recommended by goose. The live workshop provided credits via Open for this configuration. Please configure the provider you have access to noting that different models may affect the performance.

This workshop has also been tested using Claude Code. If you prefer to use Claude Code, rename the Agents.md file in the starter repo to CLAUDE.md and follow the instructions for setting up streamable HTTP MCP servers in the Claude code documentation.

Configure OpenRouter in Goose

Next, we'll configure Open as our LLM provider in Goose.

  1. Run goose configure.
  2. Select Configure Providers.
  3. Select OpenRouter.
  4. Paste your provisioned OpenRouter API key.
  5. Select anthropic/claude-sonnet-4 as your model.
  6. Use the default timeout.
  7. Leave the headers and other values as the defaults.

Screenshot of all terminal commands to configure open router

Task!

Configure GraphOS MCP tools and Built-In Extensions in Goose

In Goose, MCP servers are called extensions.

For this workshop you will add an extension for the MCP tools and configure some of the default in Goose.

Add default goose extensions (if you have never used goose extensions before)

  1. Run goose configure.
  2. Select Add Extension (Connect to a new extension).
  3. Select Built-in Extension (Use an extension that comes with goose).
  4. Select computercontroller
  5. Use the default timeout
  6. Repeat these steps to add the developer extension.

Screenshot of all terminal commands to configure goose extensions

Task!

Add the GraphOS MCP tools extension

  1. Run goose configure.

  2. Select Add Extension (Connect to a new extension).

  3. Select Remote Extension (Streaming HTTP).

  4. Name the extension graphos-mcp-tools.

    graphos-mcp-tools
  5. Add the URL: https://mcp.apollographql.com.

    https://mcp.apollographql.com
  6. Use the default timeout.

  7. We are not using headers

  8. Other values can be whatever you like or the defaults.

Task!

Toggle active extensions

  1. Run goose configure.
  2. Select Toggle Extensions.
  3. Ensure that computercontroller, developer, and graphos-mcp-tools are active. All other can be toggled off.

Install the Rover CLI

You need at least version v0.35.0 to complete the workshop.

  1. Open up a terminal and run the install command that suits your computer's environment:

    For Linux / Mac OS:

    curl -sSL https://rover.apollo.dev/nix/latest | sh

    For Windows PowerShell installer

    iwr 'https://rover.apollo.dev/win/latest' | iex

    Note: You can find other installation methods in the Apollo documentation.

  2. Verify that the installation completed successfully by running rover anywhere in the terminal.

  3. If it outputs a list of options and subcommands for using , great! The CLI is installed and ready to go.

Task!

Helpful links

Next