Connect Gemini CLI

Before you start

Gemini CLI is a good option if your team already works in Google’s AI stack and your Gemini CLI setup supports remote MCP. An Enginy admin just needs to enable the MCP integration for the workspace — that’s it to get started. Enginy grants full access by default; restricting policy scopes is an optional, advanced step for later.

Add the hosted server

Open ~/.gemini/settings.json (or .gemini/settings.json for a project-level setup) and add Enginy:

{
  "mcpServers": {
    "enginy": {
      "url": "https://openapi.enginy.ai/mcp",
      "oauth": {
        "enabled": true
      }
    }
  }
}

Restart Gemini CLI, then start the OAuth flow:

/mcp auth enginy

Gemini CLI opens the Enginy browser approval flow. This requires a local browser and will not complete over a headless or browserless SSH session.

Verify the connection

After authorization, ask Gemini CLI to use Enginy MCP and run:

mcp_whoami

That confirms the hosted MCP server is reachable, OAuth completed, and the granted scopes match what Enginy approved.

Client support matrix

Compare support levels and setup shapes across every Enginy MCP client.

Security and troubleshooting

Debug auth, scope, token, and transport issues after Gemini CLI connects.

Getting started

Clients

Guides

Reference

Before you start

Add the hosted server

Verify the connection

Client support matrix

Security and troubleshooting

​Before you start

​Add the hosted server

​Verify the connection

Client support matrix

Security and troubleshooting

Before you start

Add the hosted server

Verify the connection