Connect MemoryCode to OpenClaw (MCP)

OpenClaw supports MCP through mcporter or a built-in MCP bridge. MemoryCode is added as a normal MCP server — not as an OpenClaw Skill package (SKILL.md style skills are a separate mechanism).

Important

Skill packages and MCP servers are different paths. For MemoryCode, always use the MCP server configuration so tools such as get_user_profile and get_expertise are registered as MCP tools.

Typical config paths

macOS / Linux: ~/.config/openclaw/mcp.json
Windows: %APPDATA%\openclaw\mcp.json

OpenClaw evolves quickly; confirm paths in the OpenClaw project documentation if yours differ.

Steps (high level)

Export memorycode-mcp.json from MemoryCode and save it on disk.
Open OpenClaw MCP settings (mcporter or built-in MCP bridge, depending on your setup).
Add a server named memorycode using the stdio configuration below.
Restart or reload MCP, then confirm the tool list includes the MemoryCode tools you expect.

Configuration snippet

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

The exact JSON shape may depend on how OpenClaw wraps MCP servers — align field names with your OpenClaw version while keeping the same command and args.

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

Full reference

More clients, diagnostics, and path copy buttons.

Open MCP setup guide →

← Back to MemoryCode