Postgres MCP Pro

Name: Postgres MCP Pro
Availability: InStock
Author: Kata Team

Read/write Postgres plus health checks, index tuning, and EXPLAIN analysis.

Requires external credentials

After connecting, this agent asks for your own API keys for third-party services to work. Only provide keys you trust this agent with — review its setup before connecting any account.

Works with

Claude (web & desktop)ChatGPT (Plus / Pro)CursorVS Code (Copilot)Claude CodeGemini CLIWindsurfClineContinueZedLM StudioGooseJetBrains AI AssistantWarpPostmanand more

Before you connect: what this agent would do

A preview derived from this agent’s definition — not a live run. Nothing runs and no key is sent until you connect. You run this server on your own machine — FindAgent never runs it.

Tools it can use (5)

list_schemas
List schemas in the database.
execute_sql
Run a SQL statement (subject to the access mode).
explain_query
EXPLAIN a query with hypothetical-index simulation.
analyze_db_health
Run database-health diagnostics.
analyze_workload_indexes
Recommend indexes for the workload.

Credentials it will ask for (1)

PostgreSQL Connection String

Safety rails that guard it

Every result is scanned for leaked secrets and prompt-injection before it reaches you — a check no agent can turn off.

How FindAgent keeps agents safe

Run locally

This MCP server runs on your own machine — FindAgent only points you at it. Run the command below, then add it to your MCP client. Nothing is hosted or proxied on our side.

terminal

uvx postgres-mcp --access-mode=unrestricted

Add it to your MCP client

Paste this into your client config (e.g. claude_desktop_config.json or a Cursor mcp.json), then restart the client.

mcp client config

{
  "mcpServers": {
    "postgres-mcp-pro": {
      "command": "uvx",
      "args": [
        "postgres-mcp",
        "--access-mode=unrestricted"
      ]
    }
  }
}

View the source repository