---
title: "OpenCode | OwlMeans"
description: "Use a local MCP server in OpenCode for the project workspace. Install Node.js 22 or newer and make npx available to OpenCode."
url: "https://owlmeans.com/docs/mcp/clients/opencode/"
lang: "en"
---

# OpenCode

![](https://owlmeans.com/_astro/mcp-clients-opencode.DJ18fWww_Z1CMIru.webp)

Use a local MCP server in OpenCode for the project workspace. Install Node.js 22 or newer and make `npx` available to OpenCode.

1.  Open the project directory.

2.  Add `owlmeans` to `opencode.json`:

    ![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.

```
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "owlmeans": {
      "type": "local",
      "command": ["npx", "-y", "@owlmeans/viable-mcp@^0.2.0", "--harness", "opencode"],
      "enabled": true,
      "timeout": 90000
    }
  }
}
```

3.  Restart OpenCode and inspect the server with its MCP status commands.
4.  Use browser authorization when OwlMeans requests access.

For hosted-only work, a remote definition uses `type: "remote"` and `url: "https://api.owlmeans.com/mcp"`. OpenCode provides `mcp auth`, `mcp list` and `mcp logout` for supported remote authorization. See the [official MCP guide](https://opencode.ai/docs/mcp-servers/).

Set only one intended definition for `owlmeans` in a session. The command array keeps arguments separate and avoids shell quoting problems.

## 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, OpenCode 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.
