Database MCP Server

DatabasesGo

A multi-database server providing AI assistants with structured database access

Available Tools

query_database

Execute SQL queries against the connected database and return the results

sql_query

get_schema

Retrieve the database schema including tables, columns, and relationships

table_name

list_tables

List all tables available in the connected database

describe_table

Get detailed information about a specific table including columns, types, and constraints

table_name

get_table_sample

Retrieve a sample of rows from a specified table

table_namelimit

manage_retention_policy

Manage data retention policies for TimescaleDB hypertables

hypertable_nameretention_period

analyze_query_performance

Analyze the performance of a SQL query and provide optimization suggestions

sql_query

Database MCP Server is a powerful tool that implements the Model Context Protocol (MCP) to enable AI assistants to interact with various database systems. It provides structured access to databases including PostgreSQL, MySQL, TimescaleDB, and others, allowing AI models to execute queries, explore schema information, and analyze data efficiently. The server acts as a bridge between AI assistants and database systems, making database operations accessible through a standardized protocol.

Overview

Database MCP Server provides a standardized way for AI assistants to interact with various database systems through the Model Context Protocol (MCP). This server enables AI models to perform database operations, explore schemas, and execute queries without needing direct database access credentials in the AI context.

Installation

Prerequisites

Go 1.20 or higher
Docker (optional, for containerized deployment)
Access to one or more supported database systems

Installation Methods

Method 1: Using Docker

Pull the Docker image:

docker pull freepeak/db-mcp-server:latest

Run the container:

docker run -p 8080:8080 -e DB_CONNECTION_STRING="postgresql://user:password@host:port/dbname" freepeak/db-mcp-server

Method 2: Building from Source

Clone the repository:

git clone https://github.com/FreePeak/db-mcp-server.git
cd db-mcp-server

Build the server:
```
make build
```
Run the server:
```
./bin/server
```

Configuration

Create a .env file based on the provided .env.example:

PORT=8080
LOG_LEVEL=info
DB_TYPE=postgres
DB_CONNECTION_STRING=postgresql://user:password@localhost:5432/mydb
QUERY_TIMEOUT=30s

Supported database types:

postgres - PostgreSQL
mysql - MySQL/MariaDB
timescaledb - TimescaleDB
sqlite - SQLite

Usage

Connecting to the Server

To connect an AI assistant to the Database MCP Server, configure your AI client with the server's endpoint. The server exposes an HTTP API that implements the Model Context Protocol.

Security Considerations

The server should be deployed in a secure environment with appropriate network controls
Use environment variables or secure secrets management for database credentials
Consider implementing authentication for the MCP server in production environments
Limit database user permissions to only what is necessary for the AI's operations

Example Configurations

PostgreSQL Configuration

DB_TYPE=postgres
DB_CONNECTION_STRING=postgresql://user:password@localhost:5432/mydb

MySQL Configuration

DB_TYPE=mysql
DB_CONNECTION_STRING=mysql://user:password@localhost:3306/mydb

TimescaleDB Configuration

DB_TYPE=timescaledb
DB_CONNECTION_STRING=postgresql://user:password@localhost:5432/timescaledb

Troubleshooting

Common issues:

Connection errors: Verify your database connection string and ensure the database is accessible from the server's network.
Permission issues: Ensure the database user has appropriate permissions for the operations you're trying to perform.
Timeout errors: Adjust the QUERY_TIMEOUT setting for complex queries that take longer to execute.

For more detailed logs, set LOG_LEVEL=debug in your environment configuration.