Skip to content
mcp/harbor
Gemini CLI

Neo — AI/ML Engineering for Gemini CLI

io.github.neoresearchai/mcpserver

AI/ML engineering MCP server for Neo — submit tasks, track execution, and retrieve outputs.

client:Gemini CLI transport:stdio runtime:pypi

Install Neo — AI/ML Engineering in Gemini CLI

~/.gemini/settings.json · windows: %USERPROFILE%\.gemini\settings.json

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

{
  "mcpServers": {
    "mcpserver": {
      "command": "uvx",
      "args": [
        "neo-mcp"
      ],
      "env": {
        "NEO_SECRET_KEY": "<NEO_SECRET_KEY>",
        "NEO_ENVIRONMENT": "<NEO_ENVIRONMENT>",
        "NEO_WORKSPACE_DIR": "<NEO_WORKSPACE_DIR>"
      }
    }
  }
}

Gemini expands $VAR and ${VAR} inside env values, so a secret can live in your shell rather than this file. Gemini CLI docs

Neo — AI/ML Engineering in other clients

Neo — AI/ML Engineering MCP server