---
title: "Codex in VS Code | OwlMeans"
description: "Use the Codex extension's MCP settings to connect OwlMeans inside your Visual Studio Code (VS Code) workspace."
url: "https://owlmeans.com/docs/mcp/clients/codex-in-vs-code/"
lang: "en"
---

# Codex in VS Code

![](https://owlmeans.com/_astro/mcp-clients-codex-in-vs-code.Bu8pcp1t_ZYtfcF.webp)

Use the Codex extension’s MCP settings to connect OwlMeans inside your Visual Studio Code (VS Code) workspace.

1.  Install the official Codex extension and sign in.

2.  Open its gear menu and select **MCP servers**.

3.  Add a server named `owlmeans` and choose **STDIO**.

    ![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.

4.  Set command `npx` and arguments `-y`, `@owlmeans/viable-mcp@^0.2.0`, `--harness`, `codex`.

5.  Save and restart the extension.

You can also edit the supported Codex configuration for detailed settings:

```
[mcp_servers.owlmeans]
command = "npx"
args = ["-y", "@owlmeans/viable-mcp@^0.2.0", "--harness", "codex"]
startup_timeout_sec = 90
tool_timeout_sec = 300
```

The extension and Codex CLI use Codex’s MCP configuration. Configure the server in the Codex surface even when other agents are installed in VS Code. The [official MCP guide](https://learn.chatgpt.com/docs/extend/mcp) explains the extension dialog and configuration fields.

If your extension version exposes configuration editing instead of an Add server dialog, use the same `mcp_servers.owlmeans` table.

## 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).

## Referenced technology

![Official visual-studio-code mark](https://owlmeans.com/_astro/visual-studio-code.D_D1Uwwt_2nrVwE.webp)

Official mark, used unchanged to identify the technology. See the owner notice below.

## Names and marks

Visual Studio Code, VS Code, TypeScript and related Microsoft marks belong to Microsoft Corporation. [Usage policy](https://code.visualstudio.com/brand).

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.
