Login to MyMemory

Connect MyMemory to Claude

Updated

Definition and quick answer

MyMemory for Claude is a Model Context Protocol (MCP) connection that lets Claude Desktop and Claude Code search, save and read your MyMemory library during a conversation.

How to connect: Run npx @everstash/mcp setup to configure Claude Desktop and Claude Code in one step, or copy the MyMemory MCP config from Add memory → MCP in the app and add it to Claude Desktop's claude_desktop_config.json (or register it with claude mcp add in Claude Code) with your sm_ API key, then restart Claude. Claude gets five tools: save_memory, search_memories, list_spaces, get_memory_by_id and delete_memory.

Connection type
Model Context Protocol (MCP), stdio or remote HTTP
Supported clients
Claude Desktop, Claude Code, claude.ai custom connectors
Authentication
MyMemory API key (sm_…)
Requirements
Node.js 18+ for the local server; none for the remote URL
Package
@everstash/mcp on npm (runs with npx)
Remote URL
https://api.mymemory.dev/v1/mcp
Tools exposed
5

Setup steps

  1. 1. Or run the setup wizard

    npx @everstash/mcp setup finds the MCP clients installed on your computer, asks which to connect and for your API key, then writes each one's config itself, backups included.

    npx @everstash/mcp setup

  2. 2. Create an API key

    Generate a key on the MyMemory dashboard (the API key card on the Overview tab). Keys start with sm_ and grant access to your account, so keep the config file private.

  3. 3. Open the MCP tab in MyMemory

    Sign in at mymemory.dev, click Add memory, and open the MCP tab. Pick your client to see its exact configuration block with a copy button, or use the one-click install button where available.

  4. 4. Add the server to Claude Desktop

    In Claude Desktop open Settings → Developer → Edit Config, paste the block from the MCP tab into claude_desktop_config.json with your API key, then fully restart Claude Desktop.

    {
  "mcpServers": {
    "everstash": {
      "command": "npx",
      "args": [
        "-y",
        "@everstash/mcp"
      ],
      "env": {
        "EVERSTASH_API_KEY": "sm_your_api_key_here"
      }
    }
  }
}

  5. 5. Or register it in Claude Code

    Claude Code registers MCP servers from the command line instead of a JSON file.

    claude mcp add everstash --scope user \
  -e EVERSTASH_API_KEY=sm_your_api_key_here \
  -- npx -y @everstash/mcp

  6. 6. Or add the remote server to claude.ai

    For Claude plans with custom connectors, add https://api.mymemory.dev/v1/mcp as a remote MCP connector in claude.ai settings instead of running anything locally, then sign in with your MyMemory account when prompted.

What Claude can do with MyMemory

MCP tools available to Claude
ToolWhat it does
save_memorySaves text, a note or a URL to your library.
search_memoriesRuns hybrid semantic and full-text search; returns up to 100 results.
list_spacesLists the spaces your account can access.
get_memory_by_idReturns the full content of one memory.
delete_memoryPreviews a memory, then deletes it only when called with confirm: true.

Limitations

  • The local server (npx @everstash/mcp) runs on your computer over stdio, so each machine needs Node.js 18+ and its own config. For clients that add a remote MCP server by URL instead, point them at https://api.mymemory.dev/v1/mcp and sign in with your MyMemory account (or send your API key as a Bearer token where the client supports headers) — nothing to install.

MyMemory + Claude FAQ

Does Claude remember my MyMemory content across chats?

Yes, while the MCP server is connected. Your memories live in MyMemory, not in Claude, so every new Claude conversation can call search_memories to retrieve them.

Can Claude delete my memories?

Only with explicit confirmation. The delete_memory tool first returns a preview and deletes nothing; it permanently deletes a memory only when called again with confirm: true.