Can I use Gemini CLI with my Google AI Pro or Ultra subscription?

Not since June 18, 2026. Google stopped serving Gemini CLI to Google AI Pro, Google AI Ultra and Gemini Code Assist for individuals. Use a Gemini API key, Vertex AI, or a Code Assist Standard or Enterprise license, or move to Antigravity CLI, which Google recommends for personal accounts.

Which key does Gemini CLI use for a remote server?

At the time of writing an HTTP server is configured with the httpUrl key. If your version names it differently, the help for its mcp command says so; the URL is the same.

Is the assistant’s access separate from mine?

It is a separate token, listed by name under Settings, and revoking it does not touch your own sign-in. But it acts as you: it inherits your role on the board, narrowed by the scopes you ticked. It can never do something you could not.

Does connecting an assistant cost extra?

No. AI assistants are free on every plan, including the free personal board, and you can connect as many as you like.

Connect Gemini CLI to your fenbs kanban board

Gemini CLI reads MCP servers from its settings file. Add fenbs and Gemini can read the kanban board, file bugs and move tasks from the terminal, under your role, signed by name. Since June 18, 2026 it needs an API key, Vertex AI or a Code Assist Standard or Enterprise license: personal Google sign-ins no longer work.

Last checked September 30, 2026

Personal Google sign-in stopped on June 18, 2026

Google stopped serving Gemini CLI to Gemini Code Assist for individuals, Google AI Pro and Google AI Ultra, so Sign in with Google no longer works on a personal account (Google’s notice (opens in a new tab)). Gemini CLI still works with a Gemini API key from Google AI Studio (GEMINI_API_KEY), with Vertex AI, or with a Gemini Code Assist Standard or Enterprise license on a company, school or Google Workspace account (Gemini CLI authentication (opens in a new tab)). Google points personal users to Antigravity CLI instead. This is only how Gemini CLI signs in to Google; the fenbs sign-in below is separate and unchanged.

Connect

Make sure Gemini CLI itself is signed in one of the ways that still works: a Gemini API key, Vertex AI, or a Code Assist Standard or Enterprise license.
Open Gemini CLI’s settings file (~/.gemini/settings.json, or the project’s .gemini/settings.json).
Add fenbs under mcpServers with the URL below.
Start Gemini CLI and run /mcp auth fenbs. A browser opens on fenbs; sign in, tick what it may do, approve.
Ask what is on your board.

settings.json

{
  "mcpServers": {
    "fenbs": {
      "httpUrl": "https://fenbs.ai/api/mcp"
    }
  }
}

If the client cannot open a browser, or only speaks stdio, use the fenbs-mcp bridge with a token from Settings, “Connect an AI assistant”: FENBS_TOKEN=… npx -y fenbs-mcp. It forwards to the same endpoint and the token holds the same role.

What it can do once connected

Read the kanban board: fenbs_list_items with filters by lane, kind or free text, and fenbs_get_item for one task with its comments.
Add tasks with fenbs_create_item — a Feature, an Enhancement or a Bug, in a lane, with a priority.
Move and edit with fenbs_update_item: change the lane, the title, the note, the kind or the priority.
Comment with fenbs_comment, and search across everything it can see with fenbs_search.
Read your AI context with fenbs_get_context and keep it current with fenbs_add_context_note, fenbs_update_context_note and fenbs_delete_context_note.
Ask fenbs_whoami first: it answers who the assistant is acting as and what it may do.

What it cannot do

Anything you cannot. The assistant acts as you and holds your role on the board, narrowed by the scopes you ticked: read, write, comment. A refusal is a sentence it can repeat to you. Revoke its token in Settings and it stops at once; everything it did stays in the history under its name.