Using Wing with Claude Code

Pro Only

Wing Pro 12 integrates Claude Code, Anthropic's AI coding agent with the IDE. You can run Claude Code in Wing's AI Agent tool, use the Tasks tool for queueing, tracking, and reviewing agent work, ask the agent to fix failed tests, debugger exceptions, or code warnings, or use the agent to better understand code and run code reviews.

Wing uses the Model Context Protocol (MCP) to give the agent access to the IDE's analysis, debugger, testing, and version control features, allowing it to work more efficiently on most complex coding problems.

If you do not already have Wing installed, download it now.

This How-To covers what Claude Code itself needs and how to set it up in Wing. The workflow that follows is described in Using Wing with an AI Agent.

Claude Code is recommended and safe to use, and is the best agent for running the Tasks Manager. See the table in AI Agent Safety, which compares the agents' safety and suitability for autonomous development.

Prerequisites

Claude Code is a separate download, installed as described in the Claude Code documentation. Wing runs the claude command, which must be on your PATH.

Wing runs Claude Code's own terminal interface inside the AI Agent tool, which needs nothing more.

Once Claude Code has been installed, quit Wing and start it again so it picks up your updated PATH.

Quick Setup

To allow Wing to use Claude Code in your project, use Set Up for AI Agent > Claude Code in the Project menu. This opens a dialog asking for the top-level directory where you want the agent to run. This defaults to the Wing project directory, but can be changed. After you submit this dialog, Wing:

authorizes use of Claude Code in this project
writes the development guides that tell the agent about this project's conventions, testing regimen, and commit policy
writes CLAUDE.md and the other files Claude Code needs in order to find Wing's MCP servers
opens the Tasks and AI Agent tools side by side

You can do the same as part of the process of creating a new Wing project, with the Set Up for AI Agent option in the New Project dialog.

Note that you can also set up other agents in your Wing project, by running the same setup process for each.

For the files Wing writes into that directory, and which of them it keeps out of version control, see Setting Up an AI Agent.

Claude Code works with projects on your local machine or on a remote host; projects that run Python in a container or cluster are not yet supported.

Authentication

Claude Code requires a Claude subscription or an Anthropic API key.

Logging into a subscription is the most common way to use Claude Code. You can do this with /login in the session, or by choosing Sign In to Claude Code from the AI Agent tool's Options menu (the ⋯ button). Claude Code signs in through your browser, and sometimes shows you a code there to paste back into the session.

To supply an API key instead, set ANTHROPIC_API_KEY in the Environment in Project Properties.

Auto-Approve, the default run mode for tasks, needs a Max, Team or Enterprise account and a recent model. With other accounts, use Ask For Approval instead. Sustained day-to-day use will also require the Max plan or comparable API spending.

Next Steps

Once Claude Code is set up, you should be able to try it out in the AI Agent tool, manage tasks from the Tasks tool, and make use of Wing's other agentic development features.

For more information, see Using Wing with an AI Agent.