Skip to main content
Glama
yawlhead91

MariaDB MCP Server

by yawlhead91
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

MariaDB MCP Server

A Model Context Protocol (MCP) server for MariaDB database operations, compatible with Claude Code and other MCP clients.

Features

This MCP server provides these standard database tools:

  • list_databases: List all accessible databases

  • list_tables: List tables in a database

  • get_table_schema: Get detailed table schema and statistics

  • execute_sql: Execute read-only SQL queries (SELECT, SHOW, DESCRIBE, EXPLAIN)

  • reload_config: Reload configuration without restarting

Related MCP server: MySQL MCP Server

Installation

Prerequisites

  • Python 3.10 or higher

  • MariaDB server running

  • uv package manager

Quick Setup

# Clone/download this repository
cd mariadb-mcp

# Install dependencies
uv sync

# Configure database connection
cp .env.example .env
# Edit .env with your MariaDB credentials

Configuration

Environment Variables

Configure your MariaDB connection using these environment variables:

MARIADB_HOST=localhost
MARIADB_PORT=3306
MARIADB_USER=root
MARIADB_PASSWORD=your_password_here
MARIADB_DATABASE=mysql

# Optional: Set logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL)
LOG_LEVEL=INFO

Local Development

For local testing, create a .env file in the project root with your database credentials.

Usage

Command Line

Run the server directly:

uv run python src/mariadb_mcp/server.py

Connect with Claude Code in another terminal:

claude-code --mcp-server "uv run python src/mariadb_mcp/server.py"

Adding to Claude Code Permanently

To add this server to your Claude Code MCP server list:

Manual Configuration

Add to your Claude Code configuration file:

Option A: Using environment file (recommended)

{
  "mcpServers": {
    "MariaDB_Server": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/mariadb-mcp/",
        "run",
        "python",
        "src/mariadb_mcp/server.py"
      ],
      "envFile": "/absolute/path/to/mariadb-mcp/.env"
    }
  }
}

Option B: Direct environment variables

{
  "mcpServers": {
    "MariaDB_Server": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/mariadb-mcp/",
        "run",
        "python",
        "src/mariadb_mcp/server.py"
      ],
      "env": {
        "MARIADB_HOST": "localhost",
        "MARIADB_PORT": "3306",
        "MARIADB_USER": "root",
        "MARIADB_PASSWORD": "your_password_here",
        "MARIADB_DATABASE": "mysql"
      }
    }
  }
}

Note: When both env and envFile are specified, env variables take precedence.

After configuration:

  1. Restart Claude Code

  2. Verify "MariaDB_Server" appears in your MCP server list

  3. Test with: "List all databases"

Available Tools

reload_config()

Reload database configuration without restarting the server.

Example: "Reload the database configuration"

list_databases()

List all databases you have access to.

Example: "List all available databases"

list_tables(database: Optional[str])

List tables in a database.

Parameters:

  • database (optional): Database name

Examples:

  • "List tables in the current database"

  • "List tables in the 'myapp' database"

get_table_schema(table_name: str, database: Optional[str])

Get detailed schema information for a table.

Parameters:

  • table_name: Table name

  • database (optional): Database name

Examples:

  • "Show schema for the 'users' table"

  • "Get table structure for 'orders' in the 'ecommerce' database"

execute_sql(query: str, database: Optional[str])

Execute read-only SQL queries.

Parameters:

  • query: SQL query to execute

  • database (optional): Database to use

Examples:

  • "Execute: SELECT * FROM users LIMIT 10"

  • "Run query: SHOW CREATE TABLE products"

  • "Execute in 'analytics' database: SELECT COUNT(*) FROM events"

Security

  • Read-only operations: Only SELECT, SHOW, DESCRIBE, EXPLAIN allowed

  • No data modification: INSERT, UPDATE, DELETE, DDL statements blocked

  • Connection pooling: Efficient resource management

  • Comprehensive logging: Full error reporting

Troubleshooting

Connection Issues

  1. Verify MariaDB is running:

    sudo systemctl status mariadb
# or on macOS with Homebrew:
brew services list | grep mariadb

  2. Test connection manually:

    mysql -h localhost -u root -p

  3. Check firewall settings for remote connections

Permission Issues

Ensure your MariaDB user has SELECT permissions:

GRANT SELECT ON *.* TO 'your_user'@'localhost';
FLUSH PRIVILEGES;

Debug Mode

For development debugging:

uv run mcp dev src/mariadb_mcp/server.py

Logging

The MariaDB MCP server includes comprehensive logging for monitoring and debugging:

Log Locations

  • Console: Real-time logs displayed in the terminal

  • Log Files: Stored in logs/mariadb_mcp.log with automatic rotation

    • Maximum file size: 10MB

    • Backup files: 5 (mariadb_mcp.log.1, mariadb_mcp.log.2, etc.)

Log Levels

Set the LOG_LEVEL environment variable to control log verbosity:

  • DEBUG: Detailed information for diagnosing problems (shows SQL queries)

  • INFO: General information about server operations (default)

  • WARNING: Something unexpected happened but the server continues

  • ERROR: An error occurred but the server continues

  • CRITICAL: A serious error occurred

Example Logging Configuration

# In your .env file
LOG_LEVEL=DEBUG  # For detailed debugging

Or in Claude Code configuration:

"env": {
  "MARIADB_HOST": "localhost",
  "MARIADB_USER": "root",
  "MARIADB_PASSWORD": "dev",
  "LOG_LEVEL": "DEBUG"
}

Log Contents

Logs include:

  • Server startup/shutdown events

  • Database connection status

  • Tool function calls and results

  • SQL query execution (DEBUG level)

  • Error messages with stack traces

  • Configuration changes

License

MIT License

Available Tools

5 tools
execute_sqlB

Execute a read-only SQL query and return results.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes
databaseNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses that the query is read-only, which is a key behavioral trait, but doesn't cover other aspects like permissions needed, rate limits, error handling, or what 'return results' entails (e.g., format, pagination). For a tool with no annotations, this leaves significant gaps in understanding its behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads key information (execute, read-only, return results) with zero waste. Every word earns its place, making it highly concise and well-structured for quick understanding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (SQL execution with 2 parameters), no annotations, and an output schema present, the description is minimally adequate. It covers the basic purpose and read-only nature, but lacks details on parameter usage, behavioral constraints, or integration with siblings. The output schema reduces the need to explain return values, but more context would be helpful for safe and effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It mentions 'SQL query' which relates to the 'query' parameter, but doesn't explain the 'database' parameter or provide any additional semantic context beyond what's inferred from parameter names. With 2 parameters and no schema descriptions, the description adds minimal value over the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('execute') and resource ('SQL query'), specifying it's read-only and returns results. It distinguishes from potential siblings like 'get_table_schema' or 'list_tables' by focusing on query execution rather than metadata retrieval. However, it doesn't explicitly differentiate from all siblings (e.g., 'reload_config' is unrelated).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for executing SQL queries, particularly read-only ones, but doesn't provide explicit guidance on when to use this versus alternatives like 'list_tables' for metadata or specify prerequisites. It mentions 'read-only' which hints at when not to use it for write operations, but lacks detailed alternatives or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_table_schemaB

Get the schema/structure of a specific table.

ParametersJSON Schema
NameRequiredDescriptionDefault
table_nameYes
databaseNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the action ('Get') but doesn't describe traits like whether it's read-only, requires permissions, returns error handling for non-existent tables, or details about the output format. The description is minimal and misses key behavioral context needed for safe and effective use.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero waste. It's front-loaded with the core purpose and appropriately sized for a simple tool, avoiding unnecessary elaboration. Every word earns its place, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (2 parameters, 1 required) and the presence of an output schema (which handles return values), the description is somewhat complete but lacks depth. It covers the basic purpose but misses behavioral details and parameter guidance. With no annotations, it should do more to compensate, making it minimally adequate but with clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the schema provides no parameter details. The description mentions 'a specific table' which hints at the table_name parameter but doesn't explain the optional database parameter or provide any syntax, format, or constraints. It adds minimal value beyond the schema, compensating slightly but inadequately for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Get') and resource ('schema/structure of a specific table'), making the purpose immediately understandable. It distinguishes from siblings like list_tables (which lists tables) and execute_sql (which runs queries), though it doesn't explicitly name these alternatives. The purpose is specific but could be slightly more precise about what 'schema/structure' entails.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing to know the table name first), exclusions, or compare it to siblings like list_tables (for discovering tables) or execute_sql (for querying data). Usage is implied by the purpose but lacks explicit context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_databasesB

List all accessible databases in the MariaDB server.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool lists databases but doesn't describe what 'accessible' means (e.g., permission-based filtering), whether the list is paginated or sorted, or what happens if no databases are accessible. This leaves significant gaps in understanding the tool's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core purpose without any wasted words. It directly answers 'what does this tool do?' in a clear and structured manner, making it easy for an agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (0 parameters, no annotations, but with an output schema), the description is minimally adequate. It states the action and resource but lacks details on behavioral aspects like permissions or output format. The presence of an output schema reduces the need to explain return values, but more context on accessibility would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and schema description coverage is 100%, so there are no parameters to document. The description appropriately doesn't discuss parameters, which is correct for this case. A baseline of 4 is applied since no parameter information is needed or expected.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List') and resource ('all accessible databases in the MariaDB server'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'list_tables' or 'get_table_schema', which would require mentioning it operates at the database level rather than table or schema level.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'list_tables' or 'execute_sql'. It doesn't mention prerequisites (e.g., needing database access) or exclusions, leaving the agent to infer usage context from the tool name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_tablesB

List all tables in a specific database.

ParametersJSON Schema
NameRequiredDescriptionDefault
databaseNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does but lacks critical details: whether it's read-only, if it requires authentication, how it handles the optional database parameter, pagination behavior, or error conditions. This leaves significant gaps for an agent to understand operational traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with zero wasted words. It's front-loaded with the core purpose and appropriately sized for a simple tool, making it highly efficient for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (one optional parameter) and the presence of an output schema (which handles return values), the description is minimally adequate. However, with no annotations and incomplete parameter guidance, it lacks depth on behavioral aspects, keeping it at a basic level of completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description partially compensates by implying the 'database' parameter's role ('in a specific database'). However, it doesn't explain parameter behavior (e.g., what happens if null/default is used, format expectations, or if it lists all tables across databases). With one parameter and some added meaning, this meets the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('List') and resource ('tables in a specific database'), making it immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'list_databases' or 'get_table_schema', which prevents a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'list_databases' (for listing databases) or 'get_table_schema' (for detailed table info), nor does it specify prerequisites or context for usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

reload_configB

Reload configuration from environment variables and .env file.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It states the action ('Reload') but doesn't disclose behavioral traits like whether it's safe, idempotent, requires permissions, or what happens on failure. It only mentions the sources, leaving key operational details unclear.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with no wasted words. It's front-loaded with the core action and specifies sources clearly, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters, annotations, or output schema (context signals indicate has_output_schema: true, but it's not provided here), the description is minimally adequate. It explains what the tool does but lacks details on behavior, output, or integration context, leaving gaps in completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are 0 parameters, and schema description coverage is 100%, so no parameter information is needed. The description doesn't add param semantics, but with no params, a baseline of 4 is appropriate as it doesn't need to compensate for gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Reload') and the resource ('configuration'), specifying the sources ('from environment variables and .env file'). It's specific but doesn't differentiate from siblings since no sibling tools handle configuration reloading, making a 5 inappropriate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives or in what context it should be invoked. The description implies it's for reloading config, but lacks explicit usage scenarios or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 5 tool updates
    • First observedexecute_sql
    • First observedget_table_schema
    • First observedlist_databases
    • First observedlist_tables
    • First observedreload_config
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: execute_sql for queries, get_table_schema for metadata, list_databases and list_tables for discovery, and reload_config for server management. An agent can easily distinguish between them without confusion.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern using snake_case (e.g., execute_sql, get_table_schema). The naming is predictable and readable throughout the set, with no deviations in style.

Tool Count4/5

With 5 tools, the count is reasonable and well-scoped for a database server, covering core operations like querying, schema inspection, and listing. It's slightly lean but functional, with no obvious bloat or thinness.

Completeness3/5

The tools cover read operations and metadata well, but there are notable gaps for a full database lifecycle: no create/update/delete operations for databases, tables, or data. This limits agents to read-only and discovery tasks, which may cause failures in broader workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MariaDB MCP Server

    bretoreta
    A
    license
    B
    quality
    D
    maintenance
    Provides secure, read-only access to MariaDB/MySQL databases, allowing users to list databases, explore table schemas, and execute SQL queries with built-in security measures.
    4
    40 npm
    4
    MIT

  • MySQL MCP Server

    jeweis
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables safe interaction with MySQL databases through SELECT queries, table structure inspection, and database schema exploration. Provides read-only access to query data and examine database metadata.
    1
    -

  • MariaDB MCP Server

    akworob
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables AI assistants to interact with MariaDB databases through schema exploration, query execution, and database statistics. Includes security features like read-only mode, parameterized queries, and connection pooling with support for both JSON and Markdown output formats.
    -

  • MariaDB-MCP

    TheNesdark
    F
    license
    A
    quality
    B
    maintenance
    Enables interaction with MariaDB/MySQL databases via MCP, supporting read-only mode, SQL execution, and schema inspection.
    6
    -