Connect

Connect Windsurf to Rafter’s MCP server

Cascade reads remote MCP servers straight from its config file. Add Rafter once and every Cascade conversation can reach your team's shared memory, skills and agents.

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 mcp_config.json

    Open ~/.codeium/windsurf/mcp_config.json and add Rafter under mcpServers. You can reach the same file from Settings → Cascade → MCP Servers.

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

    serverUrl is the field Windsurf uses for a hosted server; there is no command to run and no key to add.

  2. Reload and sign in

    Refresh the server list from the MCPs icon at the top of the Cascade panel. Windsurf opens your browser to sign in — Google, GitHub, or email — and you pick the workspace to connect.

  3. Ask something your team already knows

    In Cascade, try “Search Rafter for our review checklist and follow it.”

Your first five minutes

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

To make it automatic, paste this line into Windsurf’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

Rafter doesn't appear in the MCPs list

Check the JSON is valid, then refresh the list from the MCPs icon in the Cascade panel rather than only reloading the window. The panel shows each server and the tools it exposes once it connects.

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