mempalace memory

https://mempalace-mcp.vercel.app/ — Register or sign in here first to create your API key (mpk...).

CommunityOnlineAPI key requiredGlobalFreeCan modify data

What it can do

  • Mempalace Status: Summarize the current user's memory palace: total drawers, counts per wing, counts per room. Use when you need grounding before writes or searches, or when the user asks what is stor
  • Mempalace Add Drawer: Persist a new memory drawer: writes to the user's D1 row, then embeds and upserts to Vectorize for later semantic search. Use when the user wants to remember something long-term
  • Mempalace Search: Search the current user's memories by meaning (Vectorize embeddings), optionally scoped to wing and/or room. Use when answering questions that depend on prior stored context, or befo

What data it sees

Do you need an account

An API key from the service settings is required

https://mempalace-mcp.vercel.app/ — Register or sign in here first to create your API key (mpk_...).

mempalace memory is the hosted MCP layer from the mempalace (Memory Palace) project: per-user memory drawers (wing/room), semantic search on Cloudflare (D1 + Vectorize + Workers AI embeddings). MCP endpoint: https://glidepath.dpdns.org/mcp . Authenticate with Authorization: Bearer or X-Mempalace-Api-Key (for Smithery Session Config / gateways). MIT license. In-server docs: MCP resources under docs://mempalace-memory/* (getting-started, authentication, tools-reference, data-model, troubleshooting).

How to connect

How to connect mempalace memory to Claude

The server address to paste into Claude settings:

https://mempalace-memory--farr1102work-bzcc.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect mempalace memory to ChatGPT

The server address to paste into ChatGPT settings:

https://mempalace-memory--farr1102work-bzcc.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect mempalace memory to Cursor

The server address to paste into Cursor settings:

https://mempalace-memory--farr1102work-bzcc.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (3)

Raw names from tools/list. Only developers need these.

mempalace_statusSummarize the current user's memory palace: total drawers, counts per wing, counts per room. Use when you need grounding before writes or searches, or when the user asks what is stored. Do not use for semantic lookup—use mempalace_search instead. Read-only. Returns JSON in MCP text: { total_drawers, wings: [{ wing, c }], rooms: [{ room, c }] }.
mempalace_add_drawerPersist a new memory drawer: writes to the user's D1 row, then embeds and upserts to Vectorize for later semantic search. Use when the user wants to remember something long-term (facts, decisions, contacts, meeting notes, checkpoints). Do not use to retrieve data—use mempalace_search. Not idempotent: each call creates a new row. Response JSON: { success, memory_id, wing, room, vectorize: { ok, len?, error? } }; vectorize.ok may be false while the row still saved.
mempalace_searchSearch the current user's memories by meaning (Vectorize embeddings), optionally scoped to wing and/or room. Use when answering questions that depend on prior stored context, or before writing to avoid duplicates. Read-only. If the index is still catching up after a recent write, mode may be like_fallback (SQL substring). Response JSON: { query, results: [{ id, text, wing, room, source_file, similarity }], filters: { wing, room }, mode: 'vectorize' | 'like_fallback' }.