Connect

Connect Gemini CLI to Rafter’s MCP server

Gemini CLI speaks streamable HTTP directly. One entry in settings.json and it can search your team's shared memory, follow its skills, and save what it learns back.

You need a Rafter account — create one if you haven’t.Takes about 2 minutes.No API keys — sign-in is OAuth, in the browser.
  1. Add Rafter to settings.json

    Add this to ~/.gemini/settings.json for every project, or to a project’s .gemini/settings.json to scope it.

    {
      "mcpServers": {
        "rafter": {
          "httpUrl": "https://app.heyrafter.xyz/api/mcp"
        }
      }
    }

    httpUrl is the streamable-HTTP field — url is the Server-Sent Events one, which is not what Rafter serves.

  2. Restart and sign in

    Restart gemini. On the first Rafter call it runs the OAuth flow in your browser, where you pick the workspace to connect.

  3. Check it connected

    Run /mcp — it lists every configured server with its status and the tools it exposes. Rafter should read as connected.

  4. Ask something your team already knows

    Try “Search Rafter: how do we deploy?” — the answer comes from your team’s skills and memories, not a guess.

Your first five minutes

The connection is the easy part. The habit is what pays: make Gemini CLI check the shared brain before it improvises. Three things to try in Gemini CLI:

To make it automatic, paste this line into Gemini CLI’s project or system instructions:

Check Rafter first: search our skills and memories before you answer, and save anything durable back with add_memory.

A longer startup prompt and a ready-made Claude Code skill live in the rafter-mcp repo.

Troubleshooting

Should I use url or httpUrl?

httpUrl. Gemini CLI uses url for Server-Sent Events and httpUrl for streamable HTTP; Rafter is the latter. Using the wrong one shows the server as disconnected under /mcp.

Which workspace should I pick when signing in?

The one whose skills and memories you want this tool to see. A connection sees exactly what you can see — your teams and your role — never more. You can connect again later and grant a different workspace.

Is my team's content used to train AI models?

No. Rafter does not use your content to train generalized or foundation models — see the privacy policy.

Give your whole team the same brain.From $29 per user — see pricing.

Create your account