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';
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 ('Lists') and grouping behavior, but lacks critical details: it doesn't specify if this is a read-only operation, what 'accessible' means (permissions?), whether results are paginated, or the output format. For a tool with zero annotation coverage, this is insufficient.

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 action ('Lists all accessible tables') and adds clarifying detail ('grouped by schema'). Every word earns its place with no redundancy or fluff.

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 params, no output schema), the description is adequate but has gaps. It covers the basic purpose and grouping behavior, but without annotations or output schema, it should ideally mention the return format (e.g., list of table names with schemas) or any limitations. It's minimally viable but not fully complete.

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 0 parameters, and schema description coverage is 100% (though empty). The description doesn't need to compensate for missing param info, and it correctly implies no inputs are required. A baseline of 4 is appropriate since there's nothing to document beyond 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 clearly states the verb ('Lists') and resource ('all accessible tables in the connected database'), and adds useful detail about grouping ('grouped by schema'). It doesn't explicitly differentiate from siblings like 'list_extensions' or 'list_storage_buckets', but the resource specificity makes the purpose clear.

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., database connection), compare to similar tools like 'list_extensions', or specify use cases (e.g., exploration vs. migration planning). This leaves the agent with minimal context for tool selection.

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/abushadab/selfhosted-supabase-mcp-basic-auth'

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