Scrubby

Cursor

Connect Scrubby to Cursor for architecture-aware AI assistance. Cursor's agent gets your codebase's domains, conventions, and history through Model Context Protocol.

Cursor is one of the most widely adopted AI editors, with full Model Context Protocol support. Wire Scrubby into Cursor and the agent stops guessing your codebase from filenames and starts writing code that fits.

Setup

1. Add the MCP server

Open Cursor Settings, go to the MCP tab, and add a new server with this configuration:

{
  "mcpServers": {
    "scrubby": {
      "url": "https://mcp.scrubby.ai/mcp"
    }
  }
}

Alternatively, drop the same JSON in .cursor/mcp.json at your project root if you want the config to travel with the repo.

2. Authenticate

The first time Cursor connects to Scrubby, it’ll prompt you to authenticate via GitHub OAuth. Sign in with your Scrubby account.

3. Index your repository

Ask Cursor’s agent to run scrubby_index with your repository name (e.g. your-org/your-repo). Indexing takes 1–3 minutes depending on repo size.

Usage

Once connected, Cursor’s agent reads Scrubby’s MCP tool descriptions and decides when to call them. You don’t have to prompt it specially — though if you want to nudge it:

  • “Use scrubby_review on this file before making changes.”
  • “Run scrubby_review_changeset on my changed files.”
  • “What domains does Scrubby see in this codebase?”

For the complete tool surface, see the MCP Tools Reference. The same tools work across all MCP-compatible editors.

Troubleshooting

See Editor Not Connecting for common issues. Quick fixes:

  • MCP server not showing up — restart Cursor after adding the config. Cursor reads MCP servers on startup.
  • Authentication loop — clear the OAuth session in your Scrubby dashboard and reconnect from Cursor.
  • Repository not indexed — ask Cursor to call scrubby_index with your repo name in owner/repo format.

Last updated