A read-only connection that lets an MCP client query a PostgreSQL database, a database system commonly used by applications. It runs locally and blocks database writes at the syntax-tree level.

Use it to run read-only PostgreSQL queries through MCP, with a DATABASE_URL connection and a list of columns such as passwords or card numbers to redact.

It allows database inspection while reducing the risk that a tool call changes stored data; selected sensitive columns can also be marked for redaction.

postgres — MCP server for Claude Code and Codex by Eszetael: A read-only connection that lets an MCP client query…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add mcp/eszetael/postgres-mcp-hardened/postgres

Clone the repo

git clone --depth 1 https://github.com/Eszetael/postgres-mcp-hardened

Made for: Claude Code, Codex, Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/eszetael/postgres-mcp-hardened/postgres.svg)](https://agentmods.dev/mcp/eszetael/postgres-mcp-hardened/postgres)

Your own site

<a href="https://agentmods.dev/mcp/eszetael/postgres-mcp-hardened/postgres"><img src="https://agentmods.dev/badge/mcp/eszetael/postgres-mcp-hardened/postgres.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

postgres scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

examples/claude_desktop_config.json · 14 lines

What it actually says

{
  "postgres": {
    "command": "npx",
    "args": [
      "-y",
      "postgres-mcp-hardened",
      "--stdio"
    ],
    "env": {
      "DATABASE_URL": "postgres://reader:YOUR_PASSWORD@localhost:5432/mydb",
      "MCP_REDACT_COLUMNS": "ssn, card_number, password"
    }
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

3d ago First seen · 14 lines scan A c813130116b8

Subscribe to this mod's changes

postgres is an MCP server published in the GitHub repository Eszetael/postgres-mcp-hardened (1 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Databases PostgreSQL ai-agents audit-log claude cursor database-security

midplane

Safe-by-default SQL guardrails for AI agents: AST-checked queries, per-table policy, audit log. Runs locally from the midplane npm package. Needs 4 environment variables to run.

midplaneai/midplane · not measured

supabase

Lets the agent manage Supabase projects: inspect tables, run SQL, handle migrations and read logs. Runs locally from the @supabase/mcp-server-supabase npm package. Needs 1 environment variable to run.

kensaurus/cursor-kenji · not measured

dbeast

MCP server "dbeast" as configured in snss10/DBeast. Runs ${workspaceFolder}/dbeast/src/server.py with python. Needs 9 environment variables to run.

snss10/DBeast · not measured

pg-context-mcp

MCP server "pg-context-mcp" as configured in mewsyy/pg-context. Runs locally from the pg-context-mcp npm package.

mewsyy/pg-context · not measured

mcp

Provision Postgres databases + webhooks from AI coding agents in one HTTP call. Runs locally from the @instanode/mcp npm package. Needs 2 environment variables to run.

InstaNode-dev/mcp · not measured

pgguard-mcp

Read-only MCP server for Postgres. A deny-by-default policy file decides which tables and columns an AI agent can see; every query runs inside a BEGIN READ ONLY transaction with a statement timeout, and every decision lands in an audit log. Runs locally from the pgguard-mcp npm package.

Azzaraell/pgguard-mcp · not measured