# Google Spanner MCP server

> Manage Spanner instances, databases and schemas, and run SQL queries and transactions against Google Cloud Spanner.

- Listing: https://mcp.tc/i/spanner
- Connect: use the server's own URL `https://spanner.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/spanner/docs/use-spanner-mcp>

## About

Connects to Google Cloud Spanner. You can list and inspect instances and configs, create or update instances, create databases, read and change schemas, create sessions, run SQL with parameters, commit transactions, check query plans and poll long-running operations.

It runs as a hosted remote endpoint at spanner.googleapis.com/mcp using streamable HTTP. Access uses Google OAuth 2.0 and IAM permissions, and the MCP endpoint must be enabled for the project first. Some tools write data or change schemas, so use IAM roles that match what you want the assistant to do.

## What it can do

- List and inspect Spanner instances and instance configs
- Create and update Spanner instances
- Create databases and list them per instance
- Read and update database schema (DDL)
- Run read-only or read-write SQL with parameters
- Commit transactions in a session
- Get query plans without executing the query
- Poll long-running operations

## Tools (16)

- `get_instance`: Get information about a Spanner instance. (read-only)
- `list_instances`: List Spanner instances in a project, with paging. (read-only)
- `list_configs`: List instance configs in a project, with paging. (read-only)
- `get_config`: Get details of a Spanner instance configuration. (read-only)
- `create_instance`: Create a Spanner instance in a project.
- `update_instance`: Update a Spanner instance.
- `create_database`: Create a Spanner database in an instance.
- `get_database_ddl`: Get the schema of a database. (read-only)
- `list_databases`: List databases in a Spanner instance. (read-only)
- `create_session`: Create a session in a database for running SQL. (read-only)
- `execute_sql`: Execute a SQL statement in a session, including writes. (can modify or delete data)
- `execute_sql_readonly`: Execute a SQL query in a read-only transaction. (read-only)
- `commit`: Commit a transaction in a session. (can modify or delete data)
- `update_database_schema`: Apply schema change statements to a database. (can modify or delete data)
- `get_operation`: Get status of a long-running operation. (read-only)
- `get_query_plan`: Get the execution plan for a SQL query without running it. (read-only)

## Example prompts

- "List the Spanner instances in my project my-project."
- "Show the schema of the orders database in instance prod-instance."
- "Run a read-only query for the 10 newest rows in the Users table."
- "Get the query plan for a SELECT on Orders filtered by CustomerId."

## Install

### Claude Code

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

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

2. Start Claude Code, type `/mcp`, pick **spanner** 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 Spanner** and paste this URL:

```url
https://spanner.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%20Spanner&connectorUrl=https%3A%2F%2Fspanner.googleapis.com%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://spanner.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://spanner.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=spanner&config=eyJ1cmwiOiJodHRwczovL3NwYW5uZXIuZ29vZ2xlYXBpcy5jb20vbWNwIn0%3D>) (opens Cursor)

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

`mcp.json`:

```json
{
  "mcpServers": {
    "spanner": {
      "url": "https://spanner.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=spanner&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fspanner.googleapis.com%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

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

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

`.vscode/mcp.json`:

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

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

`config.toml`:

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

### Gemini CLI

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

Then, inside Gemini CLI, run `/mcp auth spanner` 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": {
    "spanner": {
      "type": "http",
      "url": "https://spanner.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://spanner.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/spanner (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report