# MemorySync MCP server

> Share one persistent AI memory across assistants, so saved context follows you between tools.

- Listing: https://mcp.tc/i/memorysync
- Connect: use the server's own URL `https://mcp.memorysync.io/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: MemorySync
- Homepage: <https://docs.memorysync.io>
- Docs: <https://docs.memorysync.io>

## About

MemorySync is an AI memory service that stores and retrieves persistent context for assistants and agents. Through its MCP endpoint, connected tools can read from and write to the same memory, so context carries over between different AI clients.

The server runs as a hosted streamable HTTP endpoint at https://mcp.memorysync.io/mcp. It requests read and write scopes (mcp:read, mcp:write). Access needs MemorySync credentials; the vendor's API and SDKs use API keys.

## What it can do

- Save memories that persist across AI tools
- Recall stored context by semantic query
- Share one memory between multiple assistants

## Example prompts

- "Remember that our enterprise plan churn drivers are billing and onboarding."
- "What do you remember about my preferences for code style?"
- "Recall what we decided about the database migration last week."

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http memorysync https://mcp.memorysync.io/mcp
```

2. Start Claude Code, type `/mcp`, pick **memorysync** and choose **Authenticate**. A browser window opens for the MemorySync sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **MemorySync** and paste this URL:

```url
https://mcp.memorysync.io/mcp
```

3. Click **Add**, then **Connect**, and sign in when MemorySync asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=MemorySync&connectorUrl=https%3A%2F%2Fmcp.memorysync.io%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://mcp.memorysync.io/mcp` and click **Add**.

3. Click **Connect** and sign in when MemorySync asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://mcp.memorysync.io/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to MemorySync to sign in.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=memorysync&config=eyJ1cmwiOiJodHRwczovL21jcC5tZW1vcnlzeW5jLmlvL21jcCJ9>) (opens Cursor)

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

`mcp.json`:

```json
{
  "mcpServers": {
    "memorysync": {
      "url": "https://mcp.memorysync.io/mcp"
    }
  }
}
```

Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=memorysync&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.memorysync.io%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"memorysync","type":"http","url":"https://mcp.memorysync.io/mcp"}'
```

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

`.vscode/mcp.json`:

```json
{
  "servers": {
    "memorysync": {
      "type": "http",
      "url": "https://mcp.memorysync.io/mcp"
    }
  }
}
```

VS Code asks you to sign in the first time the server starts.

### Devin Desktop

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

`mcp_config.json`:

```json
{
  "mcpServers": {
    "memorysync": {
      "serverUrl": "https://mcp.memorysync.io/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add memorysync --url https://mcp.memorysync.io/mcp
codex mcp login memorysync
```

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

`config.toml`:

```toml
[mcp_servers.memorysync]
url = "https://mcp.memorysync.io/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http memorysync https://mcp.memorysync.io/mcp
```

Then, inside Gemini CLI, run `/mcp auth memorysync` to sign in.

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

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "memorysync": {
      "type": "http",
      "url": "https://mcp.memorysync.io/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://mcp.memorysync.io/mcp`.

## Details

- Last checked: 2026-11-18 (reachable, asks for credentials)
- Listed: 2026-10-27
- Updated: 2026-10-27

---
Source: https://mcp.tc/i/memorysync (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
