Connect

Connect OpenCode to Rafter’s MCP server

OpenCode takes remote MCP servers natively — no bridge, no API key. One block in opencode.json and its agent can search your team's shared memory, follow its skills, and write learnings 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 opencode.json

    Add this mcp entry to opencode.json in your project root. OpenCode reads a global config too, if you would rather have Rafter everywhere.

    {
      "$schema": "https://opencode.ai/config.json",
      "mcp": {
        "rafter": {
          "type": "remote",
          "url": "https://app.heyrafter.xyz/api/mcp",
          "enabled": true
        }
      }
    }

    The "remote" type is what tells OpenCode this is a hosted HTTP server rather than a command to run.

  2. Sign in and pick a workspace

    OpenCode notices Rafter’s sign-in requirement on the first call and opens the browser itself. Pick the workspace to connect. You can also start it by hand with opencode mcp auth rafter.

  3. Ask something your team already knows

    Try “Check Rafter: how do we handle a new client?” — the answer comes from your team’s own memories and skills.

Your first five minutes

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

To make it automatic, paste this line into OpenCode’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

Do I need an API key?

No. Rafter authenticates with OAuth in the browser, and OpenCode handles that flow for remote servers on its own — there is no token to paste or store in the config file.

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