# Google AlloyDB MCP server

> Manage AlloyDB for PostgreSQL clusters, instances, backups and users, and run SQL against your databases.

- Listing: https://mcp.tc/i/alloydb
- Connect: use the server's own URL `https://alloydb.googleapis.com/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: [Databases & Backend](https://mcp.tc/c/databases)
- Vendor: Google Cloud
- Verified: yes, mcp.tc checked that this is the official server (https://mcp.tc/verify). It says who runs the server, not that it is safe.
- Homepage: <https://docs.cloud.google.com/alloydb/docs/ai/use-alloydb-mcp>

## About

Connects to Google Cloud AlloyDB for PostgreSQL. You can list and create clusters and instances, update instance settings, create backups, restore clusters, manage IAM-based database users, import and export data through Cloud Storage, and run SQL statements, including a read-only mode.

Runs as a hosted remote endpoint at alloydb.googleapis.com/mcp over streamable HTTP. Access uses Google OAuth 2.0 and IAM permissions on your project. The MCP endpoint must be enabled for the project before use. Long-running operations such as cluster creation are tracked with a status tool.

## What it can do

- List, inspect and create AlloyDB clusters
- Create, inspect and update instances
- Create backups and restore clusters
- Create and list IAM-based database users
- Run SQL statements or read-only queries
- Import and export data via Cloud Storage
- Check status of long-running operations

## Tools (17)

- `list_clusters`: List all clusters in a project and location. (read-only)
- `create_cluster`: Create an AlloyDB cluster; returns a long-running operation.
- `get_cluster`: Get details of a cluster. (read-only)
- `list_instances`: List all instances in a cluster. (read-only)
- `restore_cluster`: Restore a cluster from a backup or a point in time.
- `create_backup`: Create a backup of a cluster in READY state.
- `create_instance`: Create a primary or read pool instance in a cluster.
- `get_instance`: Get details of an instance. (read-only)
- `update_instance`: Update instance settings such as machine type, flags or node count.
- `create_user`: Create an IAM-based database user in a cluster.
- `get_user`: Get a user in a cluster. (read-only)
- `list_users`: List all users in a cluster. (read-only)
- `execute_sql`: Execute a SQL statement on an instance, including writes. (can modify or delete data)
- `execute_sql_read_only`: Execute a SQL query on an instance in read-only mode. (read-only)
- `export_data`: Export cluster data to a Cloud Storage file as SQL or CSV.
- `import_data`: Import SQL or CSV data from Cloud Storage into a cluster.
- `get_operation`: Get the status of a long-running operation. (read-only)

## Example prompts

- "List all AlloyDB clusters in my project in us-central1"
- "Create a backup of the cluster named orders-prod"
- "Run a read-only query to count rows in the customers table"
- "Add a primary instance with 4 vCPUs to my new cluster"

## Install

### Claude Code

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

```bash
claude mcp add --transport http alloydb https://alloydb.googleapis.com/mcp
```

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

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

### Claude Desktop

1. Open **Settings → Connectors** and click **Add custom connector**.

2. Name it **Google AlloyDB** and paste this URL:

```url
https://alloydb.googleapis.com/mcp
```

3. Click **Add**, then **Connect**, and sign in when Google Cloud 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=Google%20AlloyDB&connectorUrl=https%3A%2F%2Falloydb.googleapis.com%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://alloydb.googleapis.com/mcp` and click **Add**.

3. Click **Connect** and sign in when Google Cloud 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, open **Settings → Security and login** and turn on **Developer mode**.

2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.

3. Paste `https://alloydb.googleapis.com/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to Google Cloud to sign in.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=alloydb&config=eyJ1cmwiOiJodHRwczovL2FsbG95ZGIuZ29vZ2xlYXBpcy5jb20vbWNwIn0%3D>) (opens Cursor)

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

`mcp.json`:

```json
{
  "mcpServers": {
    "alloydb": {
      "url": "https://alloydb.googleapis.com/mcp"
    }
  }
}
```

Cursor shows **Needs login** next to the server. Click it to sign in.

### VS Code

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

Or from a terminal:

```bash
code --add-mcp '{"name":"alloydb","type":"http","url":"https://alloydb.googleapis.com/mcp"}'
```

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

`.vscode/mcp.json`:

```json
{
  "servers": {
    "alloydb": {
      "type": "http",
      "url": "https://alloydb.googleapis.com/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": {
    "alloydb": {
      "serverUrl": "https://alloydb.googleapis.com/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 alloydb --url https://alloydb.googleapis.com/mcp
codex mcp login alloydb
```

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

`config.toml`:

```toml
[mcp_servers.alloydb]
url = "https://alloydb.googleapis.com/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http alloydb https://alloydb.googleapis.com/mcp
```

Then, inside Gemini CLI, run `/mcp auth alloydb` 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": {
    "alloydb": {
      "type": "http",
      "url": "https://alloydb.googleapis.com/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://alloydb.googleapis.com/mcp`.

## Details

- Server version: ESF
- MCP protocol version: 2025-11-25
- Last checked: 2026-10-03 (reachable)
- Listed: 2026-10-03
- Updated: 2026-10-03

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