---
title: "Claude Code desktop | OwlMeans"
description: "Use a local Code session in the Claude desktop app when you want the agent to work with workspace files. Desktop chat and Code sessions are different surfaces."
url: "https://owlmeans.com/docs/mcp/clients/claude-code-desktop/"
lang: "en"
---

# Claude Code desktop

![](https://owlmeans.com/_astro/mcp-clients-claude-code-desktop.DBZuIvEa_wePU1.webp)

Use a **local Code session** in the Claude desktop app when you want the agent to work with workspace files. Desktop chat and Code sessions are different surfaces.

1.  Open the project in the app’s Code tab as a local session.

2.  Add or manage the server through **Connectors**, or use the project `.mcp.json` definition below.

    ![OwlMeans MCP settings: 1, inference preference; 2, client setup tabs.](https://owlmeans.com/_astro/mcp-settings.C46Z_RMB_zICmB.webp)

    OwlMeans MCP settings: 1, inference preference; 2, client setup tabs.

3.  Save the definition and start a new Code session.

4.  Verify `owlmeans` is connected before asking it to modify source.

```
{
  "mcpServers": {
    "owlmeans": {
      "command": "npx",
      "args": ["-y", "@owlmeans/viable-mcp@^0.2.0", "--harness", "claude-code"]
    }
  }
}
```

Desktop local Code sessions can read project MCP configuration. If the same server is defined in several supported locations, avoid keeping conflicting definitions. The standalone Claude Code CLI does not automatically read desktop-chat configuration. See the [official desktop guide](https://code.claude.com/docs/en/desktop).

For a hosted-only chat connection, follow [Claude chat](https://owlmeans.com/docs/mcp/clients/claude-chat).

## Check the connection

1.  Complete OwlMeans browser sign-in when requested.
2.  Ask the agent to call `describe_platform` and `session_status`.
3.  Verify the intended project, workspace and inference mode.
4.  Ask it to inspect or [install the project harness](https://owlmeans.com/docs/mcp/install-and-use-your-project-harness).
5.  Start a small [generation or story workflow](https://owlmeans.com/docs/mcp/workflows/generate-an-app-and-develop-its-user-stories).

The examples use a **local target**. Add `--target`, `cloud` as separate arguments for a hosted project. Add `--llm`, `local` for delegated inference only when the connected coding agent will handle tasks. [Mode selection](https://owlmeans.com/docs/mcp/choose-project-location-and-inference-mode) explains the effects and costs.

Keep access tokens out of committed configuration. Restart the client after changing the server settings. If a tool is absent, inspect the connected server’s tool list and [troubleshoot](https://owlmeans.com/docs/mcp/troubleshoot-your-mcp-connection).

## Names and marks

OpenAI, ChatGPT and related OpenAI marks belong to OpenAI; Codex is an OpenAI product. [Usage policy](https://openai.com/brand/).

Claude and Claude Code are Anthropic products; their names and marks remain with their respective owner. [Usage policy](https://www.anthropic.com/legal/commercial-terms).

Node.js, npx names and any associated marks remain with their respective owners or project maintainers. References identify products, standards or source examples. OwlMeans documentation does not imply sponsorship or endorsement by those owners.
