MariaDB MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_databasesB | List all accessible databases on the MariaDB server |
| list_tablesC | List all tables in a specified database |
| describe_tableB | Show the schema for a specific table |
| execute_queryC | Execute a SQL query |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap: describe_table shows table schemas, execute_query runs SQL queries, list_databases enumerates databases, and list_tables lists tables within a database. The boundaries are well-defined, preventing agent misselection.
All tool names follow a consistent verb_noun pattern (describe_table, execute_query, list_databases, list_tables) with clear, descriptive verbs. There are no deviations in style or convention, making the set predictable and readable.
Four tools is reasonable for a MariaDB server, covering core operations like listing databases/tables, describing schemas, and executing queries. It feels slightly thin as it lacks CRUD operations (e.g., create_table, insert_data), but it's well-scoped for basic database inspection and query execution.
The tools provide good coverage for database inspection and query execution, but there are notable gaps in CRUD operations (e.g., no create_table, update_data, or delete_table). Agents can work around this using execute_query, but the surface is incomplete for full database management workflows.