Skip to main content
Glama
bretoreta

MariaDB MCP Server

by bretoreta

list_tables

Retrieve all table names from a MariaDB database to explore its structure and contents. Specify a database name or use the default to view available tables.

Instructions

List all tables in a specified database

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
databaseNoDatabase name (optional, uses default if not specified)

Implementation Reference

  • Handler for the list_tables tool: extracts database from args, runs SHOW FULL TABLES query via executeQuery helper, returns JSON stringified rows.
    case "list_tables": {
      const db = args.database as string | undefined;
      const { rows } = await executeQuery("SHOW FULL TABLES", [], db);
      return {
        content: [{ type: "text", text: JSON.stringify(rows, null, 2) }],
      };
    }
  • Input schema for list_tables tool: object with optional 'database' string property.
    inputSchema: {
      type: "object",
      properties: { database: { type: "string" } },
    },
  • src/index.ts:80-114 (registration)
    Registration of list_tables tool in the ListToolsRequestSchema handler, defining name, description, and schema.
    mcpServer.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: [
        {
          name: "list_databases",
          description: "List all databases",
          inputSchema: { type: "object" },
        },
        {
          name: "list_tables",
          description: "List tables in a database",
          inputSchema: {
            type: "object",
            properties: { database: { type: "string" } },
          },
        },
        {
          name: "describe_table",
          description: "Show schema of a table",
          inputSchema: {
            type: "object",
            properties: { database: { type: "string" }, table: { type: "string" } },
            required: ["table"],
          },
        },
        {
          name: "execute_query",
          description: "Run an arbitrary SQL query",
          inputSchema: {
            type: "object",
            properties: { query: { type: "string" }, database: { type: "string" } },
            required: ["query"],
          },
        },
      ],
    }));
  • Supporting executeQuery function called by list_tables handler to perform the SQL query on the database.
    export async function executeQuery(
      sql: string,
      params: any[] = [],
      database?: string
    ): Promise<{ rows: any; fields: mariadb.FieldInfo[] }> {
      console.error(`[Query] Executing: ${sql}`);
      // Create connection pool if not already created
      if (!pool) {
        console.error("[Setup] Connection pool not found, creating a new one");
        pool = createConnectionPool();
      }
      try {
        // Get connection from pool
        if (connection) {
          console.error("[Query] Reusing existing connection");
        } else {
          console.error("[Query] Creating new connection");
          connection = await pool.getConnection();
        }
    
        // Use specific database if provided
        if (database) {
          console.error(`[Query] Using database: ${database}`);
          await connection.query(`USE \`${database}\``);
        }
        if (!isAlloowedQuery(sql)) {
          throw new Error("Query not allowed");
        }
        // Execute query with timeout
        const [rows, fields] = await connection.query({
          metaAsArray: true,
          namedPlaceholders: true,
          sql,
          ...params,
          timeout: DEFAULT_TIMEOUT,
        });
    
        // Apply row limit if result is an array
        const limitedRows =
          Array.isArray(rows) && rows.length > DEFAULT_ROW_LIMIT
            ? rows.slice(0, DEFAULT_ROW_LIMIT)
            : rows;
    
        // Log result summary
        console.error(
          `[Query] Success: ${
            Array.isArray(rows) ? rows.length : 1
          } rows returned with ${JSON.stringify(params)}`
        );
    
        return { rows: limitedRows, fields };
      } catch (error) {
        if (connection) {
          connection.release();
          console.error("[Query] Connection released with error");
        }
        console.error("[Error] Query execution failed:", error);
        throw error;
      } finally {
        // Release connection back to pool
        if (connection) {
          connection.release();
          console.error("[Query] Connection released");
        }
      }
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

C2.9/5.0
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 disclosing behavior. It only states the basic function but does not elaborate on side effects, read-only nature, error handling (e.g., what if the database doesn't exist), or the meaning of 'default' database. This lack of detail limits transparency.

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 sentence with no redundant information. It is concise and to the point, using no filler words.

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 (one optional parameter, no output schema), the description is minimally adequate. However, it misses details like what 'default' database refers to or whether the tool requires any privileges. It does not fully prepare the agent for all usage scenarios.

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 100% for the single parameter 'database', which already explains its optionality and default behavior. The description adds no additional semantic value beyond restating 'in a specified database', which is already implicit from the 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 'List all tables in a specified database' clearly identifies the action (list) and resource (tables), distinguishing it from sibling tools like list_databases (lists databases) and describe_table (describes a single table). However, the word 'specified' implies the database parameter is required, while the schema marks it as optional, causing minor ambiguity.

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 such as describe_table or execute_query. There is no mention of prerequisites, limitations, or explicit when-to-use/when-not-to-use instructions, leaving the agent to infer appropriate usage.

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