Skip to main content

VS Code integration

Copy for LLM

Visual Studio Code (VS Code) is Microsoft's code editor. Its agent plugins are prepackaged bundles of agent customizations - skills, agents, and MCP servers - that you install from a plugin marketplace and use in chat.

The Apify plugin is published in the Awesome Copilot marketplace, which VS Code registers by default. It connects VS Code to Apify's library of Actors and bundles:

  • The Apify MCP server for searching Apify Store, running Actors, and retrieving datasets through the Model Context Protocol (MCP).
  • An apify routing agent that picks the right tool or skill from a natural-language request.
  • Five built-in skills for common workflows (see Bundled skills below).

This guide covers installation from the plugin marketplace in VS Code. It's the same plugin that powers the GitHub Copilot CLI and the GitHub Copilot desktop app.

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 If you find outdated content, please submit an issue on GitHub.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

  • An Apify account - sign up for free if you don't have one.
  • VS Code version 1.120 or newer, with AI features enabled and signed in.
  • Agent plugin support enabled - set chat.plugins.enabled to true in Settings.

Install the plugin

  1. Open the Extensions view (Ctrl + Shift + X, or Cmd + Shift + X on macOS) and enter @agentPlugins in the search field. Alternatively, run Chat: Plugins from the Command Palette (Ctrl + Shift + P, or Cmd + Shift + P on macOS).

  2. Find the apify plugin in the list. Type apify after the filter to narrow the results. The entry is labeled github/awesome-copilot#marketplace.

  3. Select Install on the apify entry.

  4. The first time you install a plugin from a marketplace, VS Code shows a trust prompt. Review the source and confirm.

The installed plugin appears in the Agent Plugins - Installed section of the Extensions view.

Authenticate to Apify

The plugin bundles the Apify MCP server (https://mcp.apify.com/), and VS Code starts it as soon as the plugin is enabled. 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. VS Code prompts that the MCP server wants to authenticate to console-backend.apify.com. Select Allow.

  2. Complete the Apify OAuth flow in your browser and choose the account to connect.

  3. Run MCP: List Servers from the Command Palette and confirm that apify-mcp-server is running.

Session persistence

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

Run your first prompt

Open Chat, select the apify agent from the mode picker, and describe what you want in natural language. The agent routes the request to the right tool or skill, so you don't need to name tools yourself.

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 through the Apify MCP server, and summarizes its inputs, pricing, and output - all without running the Actor.

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

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 Authenticate to Apify. 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.

Manage the plugin

  • To update the plugin, run Extensions: Check for Extension Updates from the Command Palette. VS Code also checks every 24 hours when extensions.autoUpdate is enabled.
  • To enable or disable the plugin, use its context menu in the Agent Plugins - Installed section of the Extensions view. Disabling it stops the bundled MCP server and hides the apify agent and skills from chat. You can disable it globally or for a single workspace.
  • To remove the plugin, right-click it in Agent Plugins - Installed and select Uninstall.

Troubleshooting

The apify plugin doesn't appear in the list

Confirm that chat.plugins.enabled is set to true and that you're running VS Code 1.120 or newer. If you overrode the chat.plugins.marketplaces setting, restore both marketplaces that VS Code registers by default:

// settings.json
"chat.plugins.marketplaces": [
    "github/awesome-copilot",
    "github/copilot-plugins"
]

The Apify MCP server doesn't start

Run MCP: List Servers from the Command Palette, select apify-mcp-server, and start or restart it. Check the Output panel (MCP: apify-mcp-server) - a successful start ends with a line about the discovered tools. In Chat, open Configure Tools and confirm that Apify MCP Server is enabled for the apify agent.

Browser doesn't open, or OAuth fails

If the browser doesn't open automatically, copy the OAuth URL from the VS Code dialog and paste it into your browser manually.

If you're running VS Code over SSH, in a dev container, or in any environment without a browser, the MCP OAuth flow can't complete. Authenticate locally first so the connection is stored, or use the Apify CLI and SDK paths instead - run apify login, or set APIFY_TOKEN with a token from Apify Console > Settings > Integrations:

export APIFY_TOKEN=<YOUR_API_TOKEN>

Installation fails with "destination path already exists"

A previous install left a cached copy of the plugin. Delete the cached directory and install again:

  • macOS: ~/Library/Application Support/Code/agentPlugins/github.com/apify/apify-github-copilot-plugin
  • Linux: ~/.config/Code/agentPlugins/github.com/apify/apify-github-copilot-plugin
  • Windows: %APPDATA%\Code\agentPlugins\github.com\apify\apify-github-copilot-plugin

The agent picks the wrong skill or transport

Start from the apify agent. It is the single entry point that detects the available transport and routes each request to the correct tool or skill.

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