Provides tools for connecting to and interacting with PostgreSQL databases, allowing users to list databases and tables, inspect schemas, and execute SQL queries with configurable permission modes (safe, write, or full).
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@sql-mcp Show me the schema for the customers table"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server for MSSQL, PostgreSQL, and SQLite database operations.
# Using bunx (recommended)
bunx @yuuzu/sql-mcp
# Using npx
npx @yuuzu/sql-mcpRelated MCP server: Database MCP Server
Multi-database support: MSSQL, PostgreSQL, and SQLite (via better-sqlite3)
8 tools for database operations
Three query modes: safe, write, full
Advanced authentication: Windows Auth (MSSQL), SSL certificates (PostgreSQL)
Tool | Description |
| Connect to a database server |
| Disconnect from the current connection |
| Check connection status and query mode |
| List all databases on the server |
| Switch to a different database |
| List all tables and views |
| Get table schema details |
| Execute SQL queries |
Control query permissions via SQL_MCP_MODE environment variable:
Mode | Allowed Operations | Description |
| SELECT, WITH, EXPLAIN | Read-only, safest |
| + INSERT, UPDATE, DELETE | Allows data modification |
| + CREATE, DROP, ALTER, TRUNCATE | Full access, use with caution |
Note:
PRAGMAstatements (e.g.PRAGMA table_info(users)) are allowed in all modes includingsafe, as they are read-only metadata queries commonly used with SQLite.
# Example: Enable write mode
SQL_MCP_MODE=write bunx @yuuzu/sql-mcpAdd to your claude_desktop_config.json:
{
"mcpServers": {
"sql-mcp": {
"command": "bunx",
"args": ["@yuuzu/sql-mcp"],
"env": {
"SQL_MCP_MODE": "safe"
}
}
}
}{
"tool": "connect-database",
"arguments": {
"engine": "mssql",
"server": "localhost",
"port": 1433,
"user": "sa",
"password": "your_password",
"database": "master"
}
}{
"tool": "connect-database",
"arguments": {
"engine": "postgres",
"server": "localhost",
"port": 5432,
"user": "postgres",
"password": "your_password",
"database": "postgres"
}
}{
"tool": "connect-database",
"arguments": {
"engine": "mssql",
"server": "localhost",
"windowsAuth": true
}
}{
"tool": "connect-database",
"arguments": {
"engine": "postgres",
"server": "your-server.com",
"user": "postgres",
"password": "your_password",
"ssl": {
"rejectUnauthorized": true,
"ca": "/path/to/ca-certificate.crt"
}
}
}{
"tool": "connect-database",
"arguments": {
"engine": "sqlite",
"filename": "/absolute/path/to/database.db"
}
}Useful for testing, demos, or ephemeral scratch workspaces.
{
"tool": "connect-database",
"arguments": {
"engine": "sqlite",
"filename": ":memory:"
}
}{
"tool": "connect-database",
"arguments": {
"engine": "sqlite",
"filename": "/absolute/path/to/database.db",
"readonly": true,
"fileMustExist": true
}
}SQLite runtime note: SQLite support uses
better-sqlite3which requires Node.js. When running viabunx, MSSQL and PostgreSQL work normally but SQLite connections will return a clear error directing you to usenpxornodeinstead.
# Install dependencies
bun install
# Run in development mode
bun run dev
# Run tests
bun test
# Run tests with coverage
bun test --coverage
# Build
bun run build
# Type check
bun run typecheckReleases are automated via GitHub Actions. To create a new release:
# Create and push a version tag
git tag v1.0.0
git push origin v1.0.0This will:
Build the project
Publish to npm with provenance
Create a GitHub Release with auto-generated release notes
Requirements: Set NPM_TOKEN secret in your GitHub repository settings.
MIT
This server cannot be deployed
Draxlr's remote MCP server connects AI assistants to your SQL databases and dashboards. Explore schemas, run read-only queries, manage saved queries and dashboards, and export results, all with row-level security so each user sees only their own data.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
The BigQuery remote MCP server is a fully managed service that uses the Model Context Protocol to connect AI applications and LLMs to BigQuery data sources. It provides secure, standardized tools for AI agents to list datasets and tables, retrieve schemas, generate and execute SQL queries through natural language, and analyze data—enabling direct access to enterprise analytics data without requiring manual SQL coding.
