MariaDB MCP Server

What does “MariaDB” MCP Server do?

The MariaDB MCP Server is a tool designed to provide AI assistants with read-only access to MariaDB databases. Acting as a Model Context Protocol (MCP) server, it enables AI-powered development workflows to connect directly to external MariaDB data sources. This integration allows AI assistants to perform tasks such as retrieving database schemas and executing read-only queries, which can be invaluable for data analytics, application development, and business intelligence. By bridging the gap between large language models and live database content, the MariaDB MCP Server facilitates secure, streamlined, and context-rich interactions that enhance developer productivity without compromising database integrity.

List of Prompts

No prompt templates are mentioned in the available documentation.

List of Resources

• Schema List Exposure
  The server exposes a list of schemas in the connected MariaDB database, allowing clients to view available data structures.
  (No other resources are explicitly mentioned.)

List of Tools

• query_database
  Allows execution of read-only operations against a MariaDB instance. This tool enables users to perform SELECT queries and retrieve data for analysis or integration into workflows.

Use Cases of this MCP Server

• Database Exploration
  Developers and data scientists can retrieve schema information and perform read-only queries to understand the structure of MariaDB databases without risking accidental modification.

• Business Intelligence
  Enables AI assistants to power dashboards or generate reports by querying live data from MariaDB databases in a secure, read-only manner.

• Application Debugging
  Developers can use the server to safely inspect and validate data within production databases, supporting troubleshooting and verification tasks.

• Automated Data Analysis
  AI tools can fetch and process database records for statistical analysis, trend identification, or machine learning model training.

How to set it up

Windsurf

No explicit instructions provided for Windsurf in the available documentation.

Claude

1. Locate the Configuration File:
   • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json
2. Add the MCP Server Configuration:
   Insert the following JSON snippet, replacing placeholders with actual values:

   {
       "mcpServers": {
           "mcp_server_mariadb": {
               "command": "/PATH/TO/uvx",
               "args": [
                   "mcp-server-mariadb",
                   "--host",
                   "${DB_HOST}",
                   "--port",
                   "${DB_PORT}",
                   "--user",
                   "${DB_USER}",
                   "--password",
                   "${DB_PASSWORD}",
                   "--database",
                   "${DB_NAME}"
               ]
           }
       }
   }
   

3. Replace Placeholders:
   • Update /PATH/TO/uvx to the full path of your uvx executable.
4. Save and Restart Claude:
   • Save the changes and restart Claude Desktop to activate the server.
5. Verify Connection:
   • Ensure the server is running and successfully connects to the MariaDB instance.

Development/Unpublished Server Example:

{
    "mcpServers": {
        "mcp_server_mariadb": {
            "command": "/PATH/TO/uv",
            "args": [
                "--directory",
                "/YOUR/SOURCE/PATH/mcp-server-mariadb/src/mcp_server_mariadb",
                "run",
                "server.py"
            ],
            "env": {
                "MARIADB_HOST": "127.0.0.1",
                "MARIADB_USER": "USER",
                "MARIADB_PASSWORD": "PASSWORD",
                "MARIADB_DATABASE": "DATABASE",
                "MARIADB_PORT": "3306"
            }
        }
    }
}

Remember to replace all placeholder paths and credentials accordingly.

Cursor

No explicit instructions provided for Cursor in the available documentation.

Cline

No explicit instructions provided for Cline in the available documentation.

Securing API Keys

When configuring your environment, use environment variables for sensitive credentials. Example:

"env": {
    "MARIADB_HOST": "127.0.0.1",
    "MARIADB_USER": "USER",
    "MARIADB_PASSWORD": "PASSWORD",
    "MARIADB_DATABASE": "DATABASE",
    "MARIADB_PORT": "3306"
}

Store values securely and never hardcode secrets in configuration files.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "mcp_server_mariadb": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change "mcp_server_mariadb" to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the above tables, the MariaDB MCP Server is simple and focused, providing essential functionality for MariaDB database access. It lacks advanced MCP features such as prompt templates or sampling, but does well in core areas such as tools, resources, and secure configuration. For a read-only database server, this is solid but basic.

MCP Score