Gemini CLI Extension - SQL Server
Note
This extension is currently in beta (pre-v1.0), and may see breaking changes until the first stable release (v1.0).
This Gemini CLI extension provides a set of tools to interact with Microsoft SQL Server instances. It allows you to manage your databases, execute queries, and explore schemas directly from the Gemini CLI, using natural language prompts.
Learn more about Gemini CLI Extensions.
Important
We Want Your Feedback! Please share your thoughts with us by filling out our feedback form. Your input is invaluable and helps us improve the project for everyone.
Why Use the SQL Server Extension?
- Natural Language Management: Stop wrestling with complex commands. Explore schemas and query data by describing what you want in plain English.
- Seamless Workflow: As a Google-developed extension, it integrates seamlessly into the Gemini CLI environment. No need to constantly switch contexts for common database tasks.
- Code Generation: Accelerate development by asking Gemini to generate data classes and other code snippets based on your table schemas.
Prerequisites
Before you begin, ensure you have the following:
- One of the supported agent harnesses, installed and authenticated:
- Gemini CLI (v0.6.0+)
- Claude Code
- Codex (v0.150.0+)
- Antigravity CLI
- Node.js (the MCP server runs via
npx). - A running SQL Server instance.
- A user with database-level permissions to execute queries.
Getting Started
Installation
All harnesses use the same plugin; the MCP server runs via npx (no binary to download). Install with your harness of choice:
Gemini CLI
gemini extensions install https://github.com/gemini-cli-extensions/sql-server
Claude Code
claude plugin marketplace add gemini-cli-extensions/sql-server
claude plugin install sql-server@sql-server
Codex
codex plugin marketplace add gemini-cli-extensions/sql-server
codex plugin add sql-server@sql-server
Antigravity
agy plugin install https://github.com/gemini-cli-extensions/sql-server
See Configuration for how each harness supplies the connection settings.
Configuration
The plugin connects to SQL Server using these settings:
MSSQL_HOST: (Optional) The SQL Server host. Defaults tolocalhost.MSSQL_PORT: (Optional) The SQL Server port. Defaults to1433.MSSQL_DATABASE: The name of the database to connect to.MSSQL_USER: The database username.MSSQL_PASSWORD: The password for the database user.
How you supply them depends on the harness:
- Gemini CLI: prompted on install and saved to the extension's
.env. View or update later withgemini extensions list/gemini extensions config sql-server [setting] [--scope user|workspace](restart the CLI to apply). - Claude Code: pass
--config KEY=VALUEon install (repeatable), or run/plugininside Claude Code. - Codex and Antigravity: export the variables in your shell before starting:
PowerShell
$env:MSSQL_HOST = '<your-sql-server-host>' # Optional: defaults to localhost
$env:MSSQL_PORT = '<your-sql-server-port>' # Optional: defaults to 1433
$env:MSSQL_DATABASE = '<your-database-name>'
$env:MSSQL_USER = '<your-database-user>'
$env:MSSQL_PASSWORD = '<your-database-password>'
Bash
export MSSQL_HOST="<your-sql-server-host>" # Optional: defaults to localhost
export MSSQL_PORT="<your-sql-server-port>" # Optional: defaults to 1433
export MSSQL_DATABASE="<your-database-name>"
export MSSQL_USER="<your-database-user>"
export MSSQL_PASSWORD="<your-database-password>"
Note
See Troubleshooting for debugging your configuration.
Start Gemini CLI
To start the Gemini CLI, use the following command:
gemini
Warning
Changing Instance & Database Connections Currently, the database connection must be configured before starting the Gemini CLI and can not be changed during a session. To save and resume conversation history use command:
/chat save <tag>and/chat resume <tag>.
Usage Examples
Interact with SQl Server using natural language right from your IDE:
- Explore Schemas and Data:
- "Show me all tables in the 'orders' database."
- "What are the columns in the 'products' table?"
- "How many orders were placed in the last 30 days, and what were the top 5 most purchased items?"
- Generate Code:
- "Generate a Python dataclass to represent the 'customers' table."
Supported Tools
list_tables: lists schema information for all or specified tables in a SQL server database.execute_sql: executes a SQL statement against a SQL Server database.
Additional Extensions
Find additional extensions to support your entire software development lifecycle at github.com/gemini-cli-extensions, including:
- Cloud SQL for SQL Server extension
- and more!
Troubleshooting
Use gemini --debug to enable debugging.
Common issues:
- "✖ Error during discovery for server: MCP error -32000: Connection closed": The database connection has not been established. Ensure your configuration is set via environment variables.
- "✖ MCP ERROR: Error: spawn npx ENOENT": Node.js/
npxis not installed or not on yourPATH. Install Node.js (which providesnpx). - "npm error"/network failures on first run:
npxfetches@toolbox-sdk/serveron first launch, so it needs network access. Retry once connectivity is available.