Skip to main content

GitHub Copilot CLI integration

Copy for LLM

The GitHub Copilot CLI is GitHub's agentic coding tool that runs in your terminal. It reads and edits your codebase, runs commands, and completes multi-step development tasks.

The Apify plugin for GitHub Copilot connects Copilot to Apify's library of Actors and bundles:

  • The Apify MCP server for searching Apify Store, running Actors, and retrieving datasets.
  • An apify routing agent that picks the right tool or skill based on your prompt.
  • Five built-in skills for common workflows.

This guide covers installation in the GitHub Copilot CLI.

Help keep this page up to date

This integration uses a third-party service. If you find outdated content, please submit an issue on GitHub.

Prerequisites

Install the plugin and sign in

The plugin is published in the Awesome Copilot marketplace, which the GitHub Copilot CLI registers by default, so you don't need to add a marketplace first. Visual Studio Code (VS Code) and the desktop app use the same marketplace. Installing the plugin also sets up the bundled Apify MCP server and signs you in, so there's no separate authentication step. Read-only tools like searching Apify Store and fetching Actor details work without signing in, but you need to authenticate to run Actors and access your account data.

  1. Install the apify plugin from the awesome-copilot marketplace:

    /plugin install apify@awesome-copilot

    This installs the plugin, its five bundled skills, and the bundled Apify MCP server (https://mcp.apify.com/). Copilot then opens a browser tab for the Apify sign-in.

  2. Complete the Apify OAuth flow in your browser and choose the account to connect. The browser confirms the authorization, and back in the terminal apify-mcp-server shows as connected.

    GitHub Copilot CLI reporting the apify plugin installed with five skills and apify-mcp-server connected

    If no browser tab opens, or apify-mcp-server doesn't connect, use the manual steps below.

Session persistence

The connection stays authenticated for future sessions. You can revoke access at any time in Apify Console > Settings > Integrations.

Connect the MCP server manually

If no browser tab opened during installation, or apify-mcp-server shows as disconnected, authenticate it from the MCP server manager.

  1. Run /mcp to open the MCP server manager, select apify-mcp-server under Plugins, and press Enter to show its details.

  2. The detail view shows the http type and the https://mcp.apify.com/ URL. Press r to authenticate.

  3. Copilot opens a browser tab for the Apify OAuth flow. If the browser doesn't open, copy the URL shown in the terminal and open it manually.

  4. Complete the OAuth flow and choose the account to connect. Back in the terminal, Copilot confirms Successfully authenticated with apify-mcp-server. Press Enter to continue.

  5. Run /mcp again to confirm apify-mcp-server is connected and enabled. Use Space to enable or disable it.

Run your first prompt

Describe what you want in plain language.

Use Apify to find a good Actor for scraping Google Maps places. Show me the best option, its input requirements, pricing model, and what kind of dataset output it returns. Do not run the Actor yet.

The agent searches Apify Store, fetches the top Actor's details, and summarizes its inputs, pricing, and output - without running the Actor.

To check what's available, ask the agent to list its Apify tools.

GitHub Copilot CLI listing the available Apify MCP tools and skills

Bundled skills

SkillDescription
apify-ultimate-scraperExtraction using existing Actors for multi-step scraping and lead-generation workflows.
apify-actor-developmentFull Actor lifecycle - template selection, development, local testing, and deployment with apify push.
apify-actorizationConverts existing JavaScript, TypeScript, Python, or CLI projects into Apify Actors.
apify-generate-output-schemaGenerates dataset and key-value store schemas for existing Actors.
apify-sdk-integrationIntegrates Actor execution into applications using the apify-client package.

Example prompts that route to specific skills:

To run apify-ultimate-scraper:

Find 10 highly rated coffee shops in Seattle with name, address, rating, phone, and website.

To run apify-actor-development:

Create an Apify Actor that accepts a startUrl and maxPages input, crawls the site, and stores each page title and URL.

To run apify-sdk-integration:

Add Apify to this project. The Node.js API route should run an Actor and return dataset items as JSON.

Authentication paths

The apify agent picks the right transport for each task. Each transport authenticates differently:

  • For MCP tools (search, run, retrieve data), authenticate with OAuth through the browser, as described in Install the plugin and sign in. You don't need to set up a token.
  • For the Apify CLI (building Actors, actorization, CLI fallback), run apify login once, or set APIFY_TOKEN in headless environments. Get your token from Apify Console > Settings > Integrations.
  • For SDK integration with apify-client, set the APIFY_TOKEN environment variable in your application's environment.

Troubleshooting

The apify plugin isn't installed

Run /plugin install apify@awesome-copilot to install the plugin from the Awesome Copilot marketplace, which the CLI registers by default. Browse the marketplace with /plugin marketplace browse awesome-copilot to confirm the apify plugin is listed.

The Apify MCP server won't authenticate

Installation normally signs you in automatically. If the browser prompt didn't appear or you skipped it, connect the server manually: run /mcp, select apify-mcp-server, and choose to authenticate, as described in Connect the MCP server manually. Read-only tools work without signing in, so run a search prompt first to confirm the server is connected.

The server is slow to connect on first start

On the first start, Copilot may report that apify-mcp-server is taking longer than expected to connect, then that it gave up waiting. The server usually finishes connecting a moment later and logs MCP server 'apify-mcp-server' connected. If it doesn't, connect it with the manual steps.

Browser doesn't open, or OAuth fails

If the browser doesn't open automatically, copy the OAuth URL shown in the terminal and paste it into your browser manually.

If you're running the CLI in a headless environment (SSH, remote container) or the OAuth flow still fails, authenticate with an API token instead. Copy your token from Apify Console > Settings > Integrations and set it before starting the CLI:

export APIFY_TOKEN=<YOUR_API_TOKEN>

The agent picks the wrong skill or transport

Start from the apify agent. It automatically detects the right transport and routes your request.

Limitations

  • Long-running Actors may time out during a single tool call. Reduce the scope or split the work across multiple prompts.
  • Each Actor run counts toward your Apify plan usage, on top of any usage your AI client bills separately. See Billing for details.
  • Skills that edit files in your project (Actor development, actorization, SDK integration) make local changes - review them before deploying or committing.

Resources