Connect MemoryCode to Cursor (MCP)
Cursor can load MCP servers from an mcp.json file. When MemoryCode is configured, Cursor-based agents can call tools that expose your identity and expertise from the local memorycode-mcp.json file you export from the app.
Before you start
- Node.js 18 or newer (includes
npx). - A saved MemoryCode export: use MCP Connect in the product to write
memorycode-mcp.jsonand note its absolute path. - Cursor build with MCP enabled — UI labels can change between versions; if steps differ, use Cursor's MCP documentation.
Config file location
Typical locations (expand ~ to your home directory if the editor requires a full path):
- macOS / Linux: ~/.cursor/mcp.json (global) or .cursor/mcp.json in a project root
- Windows: %USERPROFILE%\.cursor\mcp.json
Add the MemoryCode server
Open your Cursor mcp.json. Ensure there is a top-level mcpServers object. Merge the following entry (use your real file path instead of the placeholder):
{
"mcpServers": {
"memorycode": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@memorycode/mcp-server",
"--file",
"/absolute/path/to/memorycode-mcp.json"
]
}
}
}Cursor expects MCP stdio servers to declare type: "stdio" where applicable. If your Cursor version uses a different shape, follow the official docs and keep the same command and args.
Restart and verify
- Fully restart Cursor.
- Open the Output panel and select MCP-related logs if the server fails to start.
- Confirm profile tools (
list_configs,load_config), chip tools (list_chips,load_chip), and identity tools (get_user_profile,get_expertise) for the MemoryCode server.
After setup — profiles & cognitive chips
MemoryCode MCP 1.1 separates profiles (identity base, switched infrequently) from cognitive chips (thinking/output mode, switched frequently in the AI). You do not need to change profiles to switch chips.
Verify tools (8 total)
- Profiles:
list_configs,load_config - Chips (1.1.0+):
list_chips,load_chip,unload_chip,get_cognitive_chip - Identity:
get_user_profile,get_expertise
Daily use (natural language)
- "List my memory profiles" →
list_configs - "Switch to my work profile" →
load_config - "What cognitive chips are available?" →
list_chips - "Switch to Rigorous Analysis chip" →
load_chip(profile must be loaded first)
When to re-export
Re-export memorycode-mcp.json from MemoryCode when you create or edit profiles or chip content. You do not need to re-export when you only switch chips inside the AI (load_chip writes to local mcp.runtime).
MCP 1.0 compatibility
Legacy 1.0 exports still work for load_config. Chip tools will prompt you to re-export an MCP 1.1 file. Website chip selection affects QuickCopy; MCP chip state in mcp.runtime does not sync back to the browser.
Full reference: MCP setup guide — daily use
If something goes wrong
Common issues: wrong path to the JSON file, missing Node/npx, or a typo inside mcp.json. The interactive manual lists error patterns and fallbacks (for example using a local dist/index.js instead of npx on restricted networks).
Full reference
Paths, copy-paste snippets, and per-OS notes live in the MCP setup guide.
Open MCP setup guide →