Skip to content
Start your 14-day trial →

Cursor IDE Setup

Connect Cursor to Nexus-Catalyst for persistent memory across your development sessions.

Cursor supports MCP (Model Context Protocol) servers natively. Once connected, Cursor’s AI can:

  • Recall prior sessions — decisions, fixes, and context from past work, in any project
  • Search your memory store mid-session with search_memories
  • Store new context at the end of a session with store_context
  • Load personas — specialized AI personalities like Jack (architecture) or Nora (documentation)
  • Cursor with MCP support — download from cursor.com
  • A Nexus-Catalyst account with an active subscription or trial — start a 14-day trial, or use your invitation if you have one

No API key is required — the NC MCP server uses OAuth, and Cursor opens a browser window so you can sign in with your NC account.

In Cursor: Agent Settings → Customize → MCPs tab → New MCP Server.

That does not open a form — it opens mcp.json directly, at ~/.cursor/mcp.json (global) or in a project root for project-only access. Add an entry under mcpServers:

~/.cursor/mcp.json
{
"mcpServers": {
"nexus-catalyst": {
"url": "https://mcp.nexus-catalyst.com/"
}
}
}

The key (nexus-catalyst) is just the label Cursor shows you — name it whatever you like. The url is the only required field: no API key, no bearer token, no transport setting. Anything asking you to paste a token is out of date.

Cursor MCP Configuration

Save the file and Cursor picks the server up. It appears in the MCPs tab with a login prompt — click it, and your browser opens the Nexus-Catalyst sign-in page. Sign in (email/password, Google, or GitHub) and approve access.

Back in the MCPs tab, the entry should show a green status with the available tools listed:

  • recall_context
  • store_context
  • search_memories
  • get_memory_detail
  • get_persona_definition
  • update_user_facts
  • integration_query
  • integration_mutate

Clicking the entry opens its configure panel, where each tool can be toggled individually — leave them all enabled:

Cursor MCP connected

Open Cursor’s AI chat and ask:

What do you remember about my current project? Use recall_context.

If you’ve stored memories before, the response will reference them. If this is a fresh account, store one first:

Store a memory that I prefer TypeScript strict mode in all new projects.

You don’t need to name tools — just ask naturally and the model picks the right one:

  • “How did we handle rate limiting in the API project?”recall_context / search_memories
  • “Pull up the full write-up of that auth fix”get_memory_detail
  • “Remember that we’re standardizing on Prisma for this repo”store_context

When recall_context returns a persona_hint, the model loads that persona via get_persona_definition. You can also ask for one by name — for example Jack (AI engineering/architecture), Betty (UX), Ed (product), or Nora (technical writing). See the full roster in Personas.

With a Linear integration configured, you can create and search issues without leaving Cursor — “Create a Linear issue for this CORS bug.” See Linear Integration.

  1. Check the URL is exactly https://mcp.nexus-catalyst.com (no trailing path)
  2. Re-trigger the OAuth flow from Agent Settings → Customize → MCPs — sessions can expire
  3. Confirm the server is reachable:
    Terminal window
    curl https://mcp.nexus-catalyst.com/.well-known/oauth-protected-resource

Your OAuth session expired. Remove and re-add the server, or use the login prompt in Agent Settings → Customize → MCPs to re-authenticate.

  1. Verify memories exist in the dashboard
  2. Use a specific query — “what database did we choose for the e-commerce project” beats “what did we discuss”
  3. Ask explicitly: “call recall_context for this topic”

Need Help?

Connecting the server exposes the tools; it does not make Cursor call them. Add the MCP Instructions as a Cursor rule so recall and storage happen on their own.