Connect MemoryCode to LM Studio (MCP)

Typical config paths

• macOS / Linux: ~/.lmstudio/mcp.json
• Windows: %USERPROFILE%\.lmstudio\mcp.json

In the app, look for Program → Install → Edit mcp.json (or search Settings / Help for "MCP"). See also LM Studio MCP documentation.

Server snippet

Add a memorycode entry alongside your other servers. Use your real absolute path to the exported JSON file:

{
  "mcpServers": {
    "memorycode": {
  "command": "npx",
  "args": [
    "-y",
    "@memorycode/mcp-server",
    "--file",
    "/absolute/path/to/memorycode-mcp.json"
  ]
}
  }
}

After saving

Restart LM Studio or reload MCP according to their current UI. Confirm profile, chip, and identity tools (list_configs through get_expertise) appear for MemoryCode.

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