Skip to content

Setup

Cursor Memory MCP: How to Add Local AI Work Memory

Wire Cursor to Wenlan's local MCP memory server so coding sessions can capture and recall project context.

Qi-Xuan LuUpdated 5 min read

Article packet

01

Workflows

02

Cursor users who want local project memory across coding sessions

03

5 min read

01

Wenlan setup installs the local daemon and MCP connector.

02

wenlan mcp add cursor writes the Cursor-side MCP configuration when supported.

03

Cursor can then use Wenlan context, capture, recall, and doctor tools.

01

Quick answer

Install Wenlan, then run ~/.wenlan/bin/wenlan mcp add cursor. Restart Cursor if needed, then verify that Wenlan tools appear and can recall a test capture.

Wenlan keeps the memory layer outside Cursor while still making it available to Cursor. That keeps context portable to Claude Code, Codex, and other MCP clients later.

02

When this problem appears

Cursor has its own project-scoped Memories and Rules, but those are Cursor-native. The gap appears when you want the same work context available to Claude Code, Codex, Claude Desktop, or another MCP client.

03

Add Cursor as a client

Treat Cursor as an MCP client connected to one local Wenlan daemon.

  • Install the Wenlan runtime once with the current setup path for your operating system.
  • Run ~/.wenlan/bin/wenlan mcp add cursor.
  • The generated Cursor config writes a global ~/.cursor/mcp.json entry.
  • Restart Cursor if the MCP tools do not appear.
  • Run the Wenlan doctor tool or a capture/recall round trip.
  • Capture decisions and handoff context, not raw chat history.

Cursor MCP setup

npx -y wenlan setup
~/.wenlan/bin/wenlan mcp add cursor
~/.wenlan/bin/wenlan doctor

04

What to check next

If Cursor and another client both write memory, use spaces when contexts should stay separate. Richer distillation and page synthesis may need a configured local model or API-key path.

Try the local memory loop

Install Wenlan, connect your AI client, and verify that capture, recall, and handoff work on your machine.

FAQ

Can Cursor and Claude Code use the same Wenlan memory?+
Yes. The shared daemon is the point: each client can read and write the same local memory layer when configured.
Does Wenlan require Cursor to upload memory to a cloud service?+
No. Wenlan's default model is local-first. Optional model or API-key paths are separate choices for richer distillation.