05799475b4
This PR updates the documentation across the repository to reflect the new installation workflow using `npx` and Node.js, replacing the previous binary download instructions. It also standardizes the prerequisites and adds helpful configuration notes for Windows users. These changes simplify the setup process for users by leveraging `npx` for executing the tools, ensuring they always use the latest version without manual binary management. It also addresses feedback from PR #2079 regarding installation clarity and Windows support. --------- Co-authored-by: Twisha Bansal <twishabansal07@gmail.com>
3.1 KiB
Cloud SQL for SQL Server Admin MCP Server
The Cloud SQL for SQL Server Model Context Protocol (MCP) Server gives AI-powered development tools the ability to work with your Google Cloud SQL for SQL Server databases. It supports connecting to instances, exploring schemas, and running queries.
Features
An editor configured to use the Cloud SQL for SQL Server MCP server can use its AI capabilities to help you:
- Provision & Manage Infrastructure - Create and manage Cloud SQL instances and users
To connect to the database to explore and query data, search the MCP store for the Cloud SQL for SQL Server MCP Server.
Prerequisites
- Node.js installed.
- A Google Cloud project with the Cloud SQL Admin API enabled.
- Ensure Application Default Credentials are available in your environment.
- IAM Permissions:
- Cloud SQL Viewer (
roles/cloudsql.viewer) - Cloud SQL Admin (
roles/cloudsql.admin)
Install & Configuration
In the Antigravity MCP Store, click the "Install" button.
You'll now be able to see all enabled tools in the "Tools" tab.
Note
If you encounter issues with Windows Defender blocking the execution, you may need to configure an allowlist. See Configure exclusions for Microsoft Defender Antivirus for more details.
Usage
Once configured, the MCP server will automatically provide Cloud SQL for SQL Server capabilities to your AI assistant. You can:
- "Create a new Cloud SQL for SQL Server instance named 'e-commerce-prod' in the 'my-gcp-project' project."
- "Create a new user named 'analyst' with read access to all tables."
Server Capabilities
The Cloud SQL for SQL Server MCP server provides the following tools:
| Tool Name | Description |
|---|---|
create_instance |
Create an instance (PRIMARY, READ-POOL, or SECONDARY). |
create_user |
Create BUILT-IN or IAM-based users for an instance. |
get_instance |
Get details about an instance. |
get_user |
Get details about a user in an instance. |
list_instances |
List instances in a given project and location. |
list_users |
List users in a given project and location. |
wait_for_operation |
Poll the operations API until the operation is done. |
Custom MCP Server Configuration
Add the following configuration to your MCP client (e.g., settings.json for Gemini CLI, mcp_config.json for Antigravity):
{
"mcpServers": {
"cloud-sql-sqlserver-admin": {
"command": "npx",
"args": ["-y", "@toolbox-sdk/server", "--prebuilt", "cloud-sql-mssql-admin", "--stdio"]
}
}
}
Documentation
For more information, visit the Cloud SQL for SQL Server documentation.