Connect

Connect Rafter to Claude Code

One command in your terminal, a browser sign-in, and Claude Code works with your team's shared memory — searching it before answering and saving 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 the server

    Run this in your terminal.

    claude mcp add --transport http rafter https://app.heyrafter.xyz/api/mcp

    That registers Rafter for the current project. Add --scope user to have it in every project.

  2. Sign in and pick a workspace

    Your browser opens to authenticate — Google, GitHub, or email — and you pick the workspace to connect. Back in the terminal, claude mcp list should show rafter as connected.

  3. Install the Rafter skill

    Optional but worth it: the ready-made Rafter skill makes Claude Code search Rafter before answering “how do we do this” questions, and write durable learnings back.

    mkdir -p .claude/skills/rafter && curl -fsSL https://raw.githubusercontent.com/0xksure/rafter-mcp/main/skill/SKILL.md -o .claude/skills/rafter/SKILL.md
  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 Claude Code check the shared brain before it improvises. Three things to try in Claude Code:

To make it automatic, paste this line into Claude Code’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

The browser didn't open for sign-in

The sign-in URL is also printed in the terminal — open it yourself, then re-run your command. /mcp inside Claude Code shows the connection and lets you re-authenticate.

How do I remove it?

claude mcp remove rafter — same scope flag as when you added it.

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 $9.99 per user — see pricing.

Create your account