Install Neo — AI/ML Engineering in Gemini CLI

What you need first

• Gemini CLI, installed.
• uv, which gives the uvx command the server starts with.
• Your own values for YOUR_NEO_SECRET_KEY,YOUR_NEO_WORKSPACE_DIR.

Steps

1. Open ~/.gemini/settings.json, or create it. For one project only, use .gemini/settings.json in that project.
2. Add this block. If the file already has mcpServers, add only the entry inside it.

{
  "mcpServers": {
    "mcpserver": {
      "command": "uvx",
      "args": ["neo-mcp==0.5.15"],
      "env": { "NEO_SECRET_KEY": "YOUR_NEO_SECRET_KEY", "NEO_WORKSPACE_DIR": "YOUR_NEO_WORKSPACE_DIR" }
    }
  }
}

3. Replace YOUR_NEO_SECRET_KEY,YOUR_NEO_WORKSPACE_DIR with your own values.
4. Save the file and restart Gemini CLI.

Check it worked

Ask Gemini CLI: List the tools of mcpserver.

If it does not start

spawn uvx ENOENT

uv is not on the PATH that Gemini CLI sees. Install it, or write the full path of uvx in the config.

The server starts, but its tools fail

A YOUR_… placeholder is still in the config, or its value is wrong.

Nothing changes after a restart

The file is not valid JSON any more. Look for a missing comma where the block was added.