Switching from Cursor to Claude? Migrate Memory Right [2026]

Cursor has no native push to Claude. You'll copy .cursorrules (and any .cursor/rules/*.mdc bodies) into a Claude Project's System Prompt, upload any repo docs/ content as Project Knowledge, and recreate Notepads as either Project Knowledge text or a prompts.md. Plan 15–30 minutes per repo. A shared MCP-based memory layer like MemoryLake lets both tools read the same source.

Three drivers in 2026:

• Long-form analysis and writing. Claude handles longer documents and conversational analysis cleanly.
• Design and architecture discussion. Many teams want a chat surface separate from the IDE for high-level planning.
• MCP-native desktop client. Claude Desktop's MCP support fits teams shipping tool-using agents.

Different scopes.

Cursor memory spans `.cursorrules` (legacy single-file project rules), *`.cursor/rules/.mdc` (structured per-rule format with metadata), Notepads (reusable prompts), and user-level Rules for AI** in Settings.

Claude memory lives inside Projects. Each Project has its own Project Knowledge (uploaded files and pasted text) plus an optional System Prompt.

A .cursorrules becomes a Project's System Prompt. Repo docs/ content becomes Project Knowledge. Notepads become Project Knowledge text or a prompts.md you can reference in chat.

Rules are files you copy.

1. Locate your repo's rules. Check .cursorrules and .cursor/rules/.
2. Read each `.mdc` rule's body. Note frontmatter context (globs, alwaysApply) and condense into prose for chat.
3. Export Notepads. Open Cursor's Notepads panel and copy each Notepad's name and content into a notepads.md.
4. Capture user-level Rules for AI. Settings → Rules for AI. Paste into cursor-user-rules.txt.
5. Gather repo docs. If docs/, README.md, or ARCHITECTURE.md matter, collect them.

End state: one folder per repo with the rules content, notepads.md, cursor-user-rules.txt, and any reference docs.

Claude expects per-Project Knowledge.

1. Create a Project per repo. Open Projects → Create Project. Name it after the repo.
2. Paste rules as the System Prompt. Combine .cursorrules and .mdc bodies into a coherent System Prompt. Mention glob-bound rules in prose ("for files under src/api/, do X").
3. Upload reference docs as Project Knowledge. Click Add Content → Upload Files. Attach README.md, ADRs, style guides, and similar.
4. Add notepads.md as Project Knowledge text. Paste the notepads collection so Claude can pull from it on request.
5. Decide on cross-Project guidance. Repeat your user-level Rules for AI across every Project that needs them — Claude has no global Memory layer.
6. Probe. Open the Project and ask a question that depends on a moved rule.

• In-IDE flow. Inline Tab acceptance and Cmd-K disappear; chat is the surface.
• `.mdc` glob behavior. Glob-based selective rule application doesn't translate; Claude reads everything in the System Prompt.
• Per-Cursor chat history. Cursor's chats stay in the IDE.
• Ongoing sync. New .cursorrules edits next week won't appear in the Claude Project unless you redo the copy.

If you keep Cursor for shipping and Claude for design discussion, the per-tool drift starts immediately. Cross-repo standards end up in two places.

MemoryLake holds those rules once and exposes them through MCP. Cursor supports MCP, and Claude Desktop reads MCP natively, so the same project context flows into both from a single endpoint.

• One source of truth. Update once; both tools see the change.
• Cross-repo standards. Team conventions live above any single repo.
• Drop-in for the next tool. Add Windsurf or Claude Code with a config change.

Step 1: Create a project and load your context

Sign in to MemoryLake, open Project Management, and click Create Project. Name it "Cursor ↔ Claude shared context." Drag reference docs (PDF, Word, Excel, PowerPoint, Markdown, or images) into the Document Drive under My Space, then open the Documents Tab and click Add Documents. Paste your .cursorrules, .mdc bodies, Notepads, and user-level rules into the Memories Tab via Add Memory.

Step 2: Generate an MCP Server endpoint

Open the MCP Servers Tab inside the project, click Add MCP Server, describe it (e.g., "Cursor + Claude bridge"), and click Generate. MemoryLake returns a Key ID, a Secret, and an Endpoint URL. Copy the Secret immediately — it is shown only once.

Step 3: Point both tools at the endpoint

In Cursor's MCP configuration (e.g., .cursor/mcp.json), add a MemoryLake server entry with the endpoint URL and the Secret as a Bearer token. Add the same MCP server to Claude Desktop's MCP config, then restart Claude.