Turbular
A MCP server allowing LLM agents to easily connect and retrieve data from any database
What is Turbular?
Turbular is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server allowing llm agents to easily connect and retrieve data from any database
A MCP server allowing LLM agents to easily connect and retrieve data from any database
This server falls under the Databases category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A MCP server allowing LLM agents to easily connect and retri
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx turbularConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Turbular
Turbular is an open-source MCP server that gives LLM agents universal connectivity to relational databases including PostgreSQL, MySQL, SQLite, BigQuery, Oracle, MS SQL, and Redshift — without requiring the agent to know each database's native driver or connection syntax. It automatically normalizes schema naming conventions and transforms LLM-generated queries to match the actual schema, so the AI can query any database using natural language regardless of naming inconsistencies. Turbular runs as a FastAPI service (best deployed via Docker) and exposes REST endpoints that MCP clients consume for schema inspection and query execution.
Prerequisites
- Docker and Docker Compose installed (recommended deployment method)
- Python 3.10+ and pip (for manual installation)
- Credentials for the database(s) you want to query (host, port, username, password, database name)
- An MCP-compatible client such as Claude Desktop or a custom LLM agent
Clone the repository
Clone the Turbular repository to your local machine.
git clone https://github.com/raeudigerRaeffi/turbular.git
cd turbularLaunch the service with Docker Compose (recommended)
Build and start the Turbular FastAPI service using the provided development Docker Compose file. The service starts on port 8000 by default.
docker-compose -f docker-compose.dev.yml up --buildAlternative: manual Python installation
If not using Docker, install dependencies and start the FastAPI server directly.
pip install -r requirements.txt
uvicorn app.main:app --reloadConnect a database via the API
Use the /get_schema endpoint to register a database connection. Provide the connection details as a POST request. For BigQuery, use /upload-bigquery-key to upload your service account key first.
curl -X POST http://localhost:8000/get_schema \
-H 'Content-Type: application/json' \
-d '{"database_type": "postgresql", "username": "user", "password": "pass", "host": "localhost", "port": 5432, "database_name": "mydb"}'Configure your MCP client to use Turbular
Point your MCP client to the running Turbular service endpoint. The service exposes /get_schema and /execute_query as the primary MCP-accessible endpoints.
Turbular Examples
Client configuration
MCP client configuration connecting to a locally running Turbular service via SSE or HTTP endpoint.
{
"mcpServers": {
"turbular": {
"url": "http://localhost:8000/mcp",
"type": "streamablehttp"
}
}
}Prompts to try
Example prompts that leverage Turbular's universal database connectivity.
- "Show me the schema of the connected PostgreSQL database"
- "Query the orders table for all orders placed in the last 30 days and sort by total value"
- "How many users signed up each month this year? Group by month."
- "List all tables in the database and describe what each one likely contains"
- "Find the top 10 customers by total revenue from the sales database"Troubleshooting Turbular
Database connection refused or authentication error
Verify the host, port, username, password, and database_name values in your connection request. If using Docker, ensure the database host is accessible from within the container — use 'host.docker.internal' instead of 'localhost' when connecting to a database on your host machine.
Docker Compose build fails with dependency errors
Ensure Docker Desktop is running and up to date. Try removing any cached layers with 'docker-compose -f docker-compose.dev.yml build --no-cache' before running up --build again.
Generated SQL queries return wrong results due to schema name mismatches
Turbular's schema normalization should handle most naming convention differences automatically. If queries still fail, use the /get_schema endpoint first to inspect the normalized schema that the LLM sees, and verify it matches your expectations.
Frequently Asked Questions about Turbular
What is Turbular?
Turbular is a Model Context Protocol (MCP) server that mcp server allowing llm agents to easily connect and retrieve data from any database It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Turbular?
Follow the installation instructions on the Turbular GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Turbular?
Turbular works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Turbular free to use?
Yes, Turbular is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Turbular Alternatives — Similar Databases Servers
Looking for alternatives to Turbular? Here are other popular databases servers you can use with Claude, Cursor, and VS Code.
Excelize
★ 20.6kGo language library for reading and writing Microsoft Excel™ (XLAM / XLSM / XLSX / XLTM / XLTX) spreadsheets
MCP Toolbox for Databases
★ 15.3kOpen source MCP server specializing in easy, fast, and secure tools for Databases.
DBHub
★ 2.8kA universal database gateway MCP server that enables AI assistants to connect to and query multiple databases (PostgreSQL, MySQL, MariaDB, SQL Server, SQLite) with support for schema exploration, SQL execution, and secure connections via SSH tunnels.
Tabularis
★ 2.1kA lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable with plugins. Built for speed, security, and aesthetics.
Postgres AI Guide
★ 1.7kMCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better PostgreSQL code.
Anyquery
★ 1.7k🏎️ 🏠 ☁️ - Query more than 40 apps with one binary using SQL. It can also connect to your PostgreSQL, MySQL, or SQLite compatible database. Local-first and private by design.
Browse More Databases MCP Servers
Explore all databases servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Turbular in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Turbular?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.