Memoryvf.sr

listing.by · home.legend.verified

Store and recall persistent memory across sessions using a local knowledge graph.

state.local.longlisting.badge.runs_with

listing.install

listing.local.explain

npx -y @modelcontextprotocol/server-memory

listing.local.needs listing.local.note

act.add_to act.add_to

listing.about

Memory is a reference MCP server that gives an assistant a knowledge-graph-based persistent memory. Information is kept between conversations so the assistant can recall it later.

It runs locally over stdio with npx (npx -y @modelcontextprotocol/server-memory) and is configured in an MCP client such as Claude Desktop. No API key is listed. The maintainers describe the repository's servers as reference implementations for learning, not production-ready solutions.

listing.can

Keep a knowledge graph of information across sessions
Let the assistant recall earlier context in new conversations
Run locally with npx, no hosted service

listing.tools

listing.notools.local

listing.prompts

Remember that I prefer TypeScript and use pnpm for all my projects.
What do you remember about my current project?
Add a note that Sarah is the lead on the billing migration.
Recall what we decided about the database schema last time.

listing.setup.h

listing.setup.local

Claude Code

Run this in a terminal, in your project folder:

claude mcp add --transport stdio memory -- npx -y @modelcontextprotocol/server-memory

Start Claude Code and type /mcp. memory should show as connected.

Add --scope user to make it available in every project.

Claude Desktop

Open Settings → Developer → Edit Config. It opens claude_desktop_config.json. Add:

claude_desktop_config.json

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    }
  }
}

Save the file and restart Claude Desktop.

Needs Node.js on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.

Cursor

Add to Cursor a11y.new_tab

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    }
  }
}

Needs Node.js on your computer.

VS Code

Install in VS Code a11y.new_tab

Or from a terminal:

code --add-mcp '{"name":"memory","type":"stdio","command":"npx","args":["-y","@modelcontextprotocol/server-memory"]}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json

{
  "servers": {
    "memory": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    }
  }
}

Needs Node.js on your computer.

Devin Desktop

Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):

mcp_config.json

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    }
  }
}

Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

Codex

codex mcp add memory -- npx -y @modelcontextprotocol/server-memory

Or edit ~/.codex/config.toml directly:

config.toml

[mcp_servers.memory]
command = "npx"
args = ["-y", "@modelcontextprotocol/server-memory"]

Needs Node.js on your computer.

Gemini CLI

gemini mcp add memory npx -- -y @modelcontextprotocol/server-memory

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients that start local servers accept this shape:

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    }
  }
}

Zed puts servers under context_servers in its settings, with the same command, args and env fields.

Needs Node.js on your computer.

listing.faq

Can I paste mcp.tc/i/memory into my MCP client?

No. Memory runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is npx -y @modelcontextprotocol/server-memory.

Does Memory need an API key?

No. It doesn't declare any keys or environment variables. It runs with your user account's permissions, so check what its tools can reach.

Is Memory a remote or a local server?

Local. Your client starts it as a process on your computer with npx -y @modelcontextprotocol/server-memory, which needs Node.js.

What can Memory do?

You can keep a knowledge graph of information across sessions, let the assistant recall earlier context in new conversations and run locally with npx, no hosted service.

Which clients can use it?

Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.

Who wrote this page?

mcp.tc's robot read Memory's public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can't confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

listing.em.h

listing.em.lead_local listing.em.how

listing.em.badge

Markdown

[![Memory on mcp.tc](https://mcp.tc/i/memory/badge.svg)](https://mcp.tc/i/memory)

HTML

<a href="https://mcp.tc/i/memory"><img src="https://mcp.tc/i/memory/badge.svg" alt="Memory on mcp.tc" height="20"></a>

listing.em.badge_note

listing.em.widget

HTML

<script src="https://mcp.tc/w/memory.js" async></script>

listing.em.widget_note

iframe

HTML

<iframe src="https://mcp.tc/embed/memory" title="Memory on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

listing.em.iframe_note