Skip to main content
Glama
abushadab

Self-Hosted Supabase MCP Server

by abushadab

list_tables

Identify all accessible tables in a self-hosted Supabase database, organized by schema, to streamline database exploration and management tasks.

Instructions

Lists all accessible tables in the connected database, grouped by schema.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The complete tool object for 'list_tables', including the execute handler function that queries the database for accessible tables, excluding system and Supabase internal schemas.
    export const listTablesTool = {
        name: 'list_tables',
        description: 'Lists all accessible tables in the connected database, grouped by schema.',
        inputSchema: ListTablesInputSchema, // Use defined schema
        mcpInputSchema: mcpInputSchema,     // Add the static JSON schema for MCP
        outputSchema: ListTablesOutputSchema,
        // Use explicit types for input and context
        execute: async (input: ListTablesInput, context: ToolContext) => {
            const client = context.selfhostedClient;
    
            // SQL query to get tables from pg_catalog and information_schema
            // Excludes system schemas like pg_catalog, information_schema, and Supabase internal schemas
            const listTablesSql = `
                SELECT
                    n.nspname as schema,
                    c.relname as name,
                    pgd.description as comment
                FROM
                    pg_catalog.pg_class c
                JOIN
                    pg_catalog.pg_namespace n ON n.oid = c.relnamespace
                LEFT JOIN
                    pg_catalog.pg_description pgd ON pgd.objoid = c.oid AND pgd.objsubid = 0
                WHERE
                    c.relkind = 'r' -- r = ordinary table
                    AND n.nspname NOT IN ('pg_catalog', 'information_schema', 'pg_toast')
                    AND n.nspname NOT LIKE 'pg_temp_%'
                    AND n.nspname NOT LIKE 'pg_toast_temp_%'
                     -- Exclude Supabase internal schemas
                    AND n.nspname NOT IN ('auth', 'storage', 'extensions', 'graphql', 'graphql_public', 'pgbouncer', 'realtime', 'supabase_functions', 'supabase_migrations', '_realtime')
                    AND has_schema_privilege(n.oid, 'USAGE')
                    AND has_table_privilege(c.oid, 'SELECT')
                ORDER BY
                    n.nspname,
                    c.relname
            `;
    
            const result = await executeSqlWithFallback(client, listTablesSql, true);
    
            return handleSqlResponse(result, ListTablesOutputSchema); // Use a helper to handle response/errors
        },
    }; 
  • Zod schema for the tool output: array of table objects with schema name, table name, and optional comment.
    const ListTablesOutputSchema = z.array(z.object({
        schema: z.string(),
        name: z.string(),
        comment: z.string().nullable().optional(), // Add comment if available
    }));
  • Zod schema for tool input: empty object since no input parameters are required.
    const ListTablesInputSchema = z.object({ // No specific input needed for listing tables
        // Optional: add schema filter later if needed
        // schema: z.string().optional().describe('Filter tables by schema name.'),
    });
  • src/index.ts:100-100 (registration)
    Registration of the listTablesTool in the availableTools object, which is used to populate the MCP server's tool capabilities.
    [listTablesTool.name]: listTablesTool as AppTool,
  • src/index.ts:11-11 (registration)
    Import statement for listTablesTool in the main index file.
    import { listTablesTool } from './tools/list_tables.js';

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.2/5.0
Behavior2/5

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

No annotations exist, so the description must fully disclose behavior. It only states the action, but omits important traits like whether it is read-only, requires authentication, or any side effects.

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 that efficiently communicates the core action and grouping. No wasted 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?

For a simple tool with no parameters and no output schema, the description is adequate but lacks details about the return format or structure of the grouped output.

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 no parameters, and schema coverage is 100%. With zero params, the baseline is 4. The description adds no parameter info, but none is needed.

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 ('lists'), the resource ('tables'), and the grouping ('grouped by schema'). It distinguishes from siblings like list_extensions or list_migrations by specifying tables, but does not explicitly say when to use it over others.

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 vs alternatives, nor any prerequisites or exclusions. The agent receives no context for decision-making.

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