Skip to main content
Glama
abushadab

Self-Hosted Supabase MCP Server

by abushadab

get_database_connections

Retrieve details of active database connections from pg_stat_activity to monitor and manage database performance and usage in a self-hosted Supabase environment.

Instructions

Retrieves information about active database connections from pg_stat_activity.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The main handler function for the get_database_connections tool. It executes a SQL query on pg_stat_activity to retrieve details of active client backend database connections, casts certain fields to text, filters backend_type, orders by backend_start, and processes the result using shared utilities.
    execute: async (input: GetDbConnectionsInput, context: ToolContext) => {
        const client = context.selfhostedClient;
    
        // Query pg_stat_activity
        // Note: Access to pg_stat_activity might require superuser or specific grants.
        const getConnectionsSql = `
            SELECT
                pid,
                datname,
                usename,
                application_name,
                client_addr::text, -- Cast inet to text
                backend_start::text, -- Cast timestamp to text
                state,
                query
            FROM
                pg_stat_activity
            WHERE
                backend_type = 'client backend' -- Exclude background workers, etc.
                -- Optionally filter out self?
                -- AND pid != pg_backend_pid()
            ORDER BY
                backend_start
        `;
    
        const result = await executeSqlWithFallback(client, getConnectionsSql, true);
    
        return handleSqlResponse(result, GetDbConnectionsOutputSchema);
    },
  • Zod schemas for input (empty object), output (array of connection objects with fields like datname, usename, etc.), and static MCP input JSON schema (empty object).
    const GetDbConnectionsOutputSchema = z.array(z.object({
        datname: z.string().nullable().describe('Database name'),
        usename: z.string().nullable().describe('User name'),
        application_name: z.string().nullable().describe('Application name (e.g., PostgREST, psql)'),
        client_addr: z.string().nullable().describe('Client IP address'),
        backend_start: z.string().nullable().describe('Time when the backend process started'),
        state: z.string().nullable().describe('Current connection state (e.g., active, idle)'),
        query: z.string().nullable().describe('Last or current query being executed'),
        pid: z.number().describe('Process ID of the backend'),
    }));
    
    // Input schema (allow filtering by user or database later if needed)
    const GetDbConnectionsInputSchema = z.object({});
    type GetDbConnectionsInput = z.infer<typeof GetDbConnectionsInputSchema>;
    
    // Static JSON Schema for MCP capabilities
    const mcpInputSchema = {
        type: 'object',
        properties: {},
        required: [],
    };
  • src/index.ts:16-16 (registration)
    Import statement that brings in the getDatabaseConnectionsTool from its implementation file.
    import { getDatabaseConnectionsTool } from './tools/get_database_connections.js';
  • src/index.ts:105-105 (registration)
    Registration of the tool in the availableTools object, which is later used to populate the MCP server capabilities and handle tool calls.
    [getDatabaseConnectionsTool.name]: getDatabaseConnectionsTool as AppTool,
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 behavioral disclosure. It states the action ('Retrieves') but doesn't cover critical aspects like whether this is a read-only operation, potential performance impacts, authentication requirements, or rate limits. This leaves significant gaps for a tool that likely accesses system-level data.

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 directly states the tool's purpose without unnecessary words. It is front-loaded and wastes no space, making it easy for an agent to parse quickly.

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

Completeness2/5

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

Given the complexity of database monitoring and the lack of annotations and output schema, the description is insufficient. It doesn't explain what information is retrieved (e.g., connection details, query status), the format of the output, or any behavioral constraints, leaving the agent with incomplete context for safe and effective use.

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 the input schema has 100% coverage (though empty). The description doesn't need to explain parameters, so it meets the baseline of 4 for parameterless tools by not introducing confusion or redundancy.

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 ('Retrieves') and resource ('information about active database connections from pg_stat_activity'), making the purpose specific and understandable. However, it doesn't explicitly differentiate from siblings like 'get_database_stats' or 'list_tables', which prevents a perfect score.

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 'get_database_stats' or 'execute_sql'. It lacks context about use cases, prerequisites, or exclusions, leaving the agent to infer usage based on the name alone.

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