Skip to main content
Glama
wirdes

db-mcp-tool

!tables

View and manage database tables across PostgreSQL, MySQL, and Firestore with this MCP tool, enabling efficient exploration and organization of structured data.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • src/index.ts:125-154 (registration)
    Registration of the '!tables' MCP tool, including the inline handler function that checks database connection and retrieves tables via dbService.getTables(), returning JSON or error.
    server.tool(
      "!tables",
      {},
      async () => {
        if (!dbService) {
          return {
            content: [{ type: "text", text: "You must connect to a database first!" }],
            isError: true,
          };
        }
    
        try {
          const tables = await dbService.getTables();
          return {
            content: [
              {
                type: "text",
                text: JSON.stringify(tables, null, 2),
              },
            ],
          };
        } catch (error: unknown) {
          const errorMessage = error instanceof Error ? error.message : 'Unknown error';
          return {
            content: [{ type: "text", text: `Failed to get table information: ${errorMessage}` }],
            isError: true,
          };
        }
      }
    );
  • The core handler logic in DatabaseService.getTables() that queries the database-specific information_schema or equivalent to fetch table names and column metadata (name, type, nullable). Supports PostgreSQL, MySQL, and Firestore.
    async getTables(): Promise<TableInfo[]> {
        switch (this.config.type) {
            case 'postgres': {
                const query = `
          SELECT 
            table_name,
            json_agg(json_build_object(
              'name', column_name,
              'type', data_type,
              'nullable', is_nullable = 'YES'
            )) as columns
          FROM information_schema.columns
          WHERE table_schema = 'public'
          GROUP BY table_name;
        `;
                const result = await this.postgresClient!.query(query);
                return result.rows.map(row => ({
                    name: row.table_name,
                    columns: row.columns
                }));
            }
            case 'mysql': {
                const [rows] = await this.mysqlConnection!.query(`
          SELECT 
            TABLE_NAME as tableName,
            GROUP_CONCAT(
              JSON_OBJECT(
                'name', COLUMN_NAME,
                'type', DATA_TYPE,
                'nullable', IS_NULLABLE = 'YES'
              )
            ) as columns
          FROM information_schema.columns
          WHERE table_schema = DATABASE()
          GROUP BY TABLE_NAME;
        `);
                return rows.map((row: any) => ({
                    name: row.tableName,
                    columns: JSON.parse(`[${row.columns}]`)
                }));
            }
            case 'firestore': {
                // Firestore'da tablo yapısı olmadığı için koleksiyonları listeleyeceğiz
                const collections = await this.firestoreClient!.listCollections();
                return collections.map(collection => ({
                    name: collection.id,
                    columns: [] // Firestore şemasız olduğu için boş bırakıyoruz
                }));
            }
            default:
                return [];
        }
    }
  • TypeScript interface definitions for TableInfo (table name and columns array) and ColumnInfo (column name, type, nullable flag), which structure the output data from !tables tool.
    export interface TableInfo {
        name: string;
        columns: ColumnInfo[];
    }
    
    export interface ColumnInfo {
        name: string;
        type: string;
        nullable: boolean;
    }
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

Install Server

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/wirdes/db-mcp-tool'

If you have feedback or need assistance with the MCP directory API, please join our Discord server