Cursor IDE Integration

Add persistent, encrypted memory to Cursor's AI assistant via the Model Context Protocol. Your coding context survives across sessions — securely.

Overview

Cursor IDE supports MCP servers, allowing its built-in AI assistant to interact with external tools. By connecting Synapse Layer, Cursor's agent gains the ability to store and recall memories across coding sessions — project preferences, architecture decisions, debugging context — all encrypted with AES-256-GCM.

Setup

Cursor supports MCP configuration via a JSON file. Create or edit .cursor/mcp.json in your project root (or the global Cursor config directory):

json
{
  "mcpServers": {
    "synapse-layer": {
      "url": "https://forge.synapselayer.org/api/mcp",
      "headers": { "x-connect-token": "sk_connect_YOUR_TOKEN" }
    }
  }
}

Note

Cursor connects to the hosted endpoint directly — no local install. Replace sk_connect_YOUR_TOKEN with your Connect Token from forge.synapselayer.org → Dashboard → Connect.

After saving the config, restart Cursor. The Synapse Layer tools will appear in Cursor's MCP tools panel.

Usage

Once connected, you can ask Cursor's AI to use Synapse Layer naturally:

You:"Remember that this project uses a monorepo with pnpm workspaces and the API is in /packages/api."
Cursor AI:Stored. I'll remember your project structure for future sessions.

Next session, different file...

You:"Where is the API code in this project?"
Cursor AI:Based on my memory, this project uses a monorepo with pnpm workspaces and the API is in /packages/api.

Project vs Global Configuration

ScopeConfig LocationUse Case
Project.cursor/mcp.jsonMemory scoped to a specific codebase. Commit to version control for team sharing.
Global~/.cursor/mcp.jsonMemory available across all projects. Personal preferences and cross-project context.

Tip

Use a separate Connect Token per project (Dashboard → Connect) to keep memory namespaces isolated — or use the same ID for cross-project memory sharing.