postgres-mcp-server CLAUDE.md

postgres-mcp-server CLAUDE.md is an instructions file for coding agents from arieffian/postgres-mcp-server. It costs 1,616 tokens per session, scanned A, original, MIT.

Project instructions for postgres-mcp-server, an MCP server that lets an agent inspect and, when enabled, change PostgreSQL databases.

In plain words
What is it for?
Use them when developing or testing database connection, SQL, metadata, schema-inspection, safety, logging, and command-line features.
Why use it?
They explain the project's architecture, technology choices, safety rules, and development commands so database-related changes follow the repository's requirements.

Instructions file

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 instructions/arieffian/postgres-mcp-server/claude-md
Clone the repo
git clone --depth 1 https://github.com/arieffian/postgres-mcp-server

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.

agentmods badge for postgres-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arieffian/postgres-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/arieffian/postgres-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/arieffian/postgres-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/arieffian/postgres-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,616 This file is loaded in full into every session.
When invoked 1,616 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01616 $0.01616
Opus 5 $0.00808 $0.00808
Sonnet 5 $0.00323 $0.00323
Haiku 4.5 $0.00162 $0.00162

Measured 3d ago against content hash 6e5d65fc2946, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

postgres-mcp-server CLAUDE.md 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.

CLAUDE.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

postgres-mcp-server

A general-purpose Model Context Protocol (MCP) server that lets an LLM query and (opt-in) mutate PostgreSQL databases safely. Node.js/TypeScript, distributed via npm.

Status: v0.2 (Phase 2). Meta, SQL, and schema introspection tools shipped; observability tools are deferred to Phase 3.

Stack

  • Node.js ≥ 20 (ESM only, "type": "module")
  • TypeScript 5.x strict (strict: true, no any in safety/ or connections/ layers)
  • @modelcontextprotocol/sdk — MCP protocol
  • pg (node-postgres) — Postgres driver + pooling
  • zod — input schemas and config validation
  • zod-to-json-schema — publishes real JSON Schema for tool inputs
  • pino — structured logging (stderr only; stdout reserved for MCP JSON-RPC)
  • commander — CLI parsing
  • vitest + @testcontainers/postgresql — unit / integration / smoke tests
  • changesets — versioning + npm publish

Architecture — three horizontal layers

Middleware runs at the dispatcher, so any new tool inherits safety guarantees.

src/
  server.ts                  # MCP stdio bootstrap, CLI, banner, shutdown
  types.ts                   # ConnectionMode, ToolContext, ToolResult, Row
  errors.ts                  # ToolError class + pgErrorToToolError
  logging.ts                 # pino + redactUrl
  config/
    schema.ts                # zod schema for the config file
    loader.ts                # discovery order + validation → { config, path }
  connections/
    manager.ts               # ConnectionManager — pool per alias, owned getClient
    session.ts               # initSessionSQL (per-mode SET statements)
    transactions.ts          # TransactionManager — uuid handles, mutex, wall-clock cap
  safety/
    middleware.ts            # assertModeAllowed (read < write < admin)
    limit-cursor.ts          # runWithCursorLimit (server-side cursor)
    result-cap.ts            # applyResultCap (byte cap, rowed + scalar paths)
  tools/
    registry.ts              # ToolRegistry: schema validate → mode gate → dispatch → cap
    index.ts                 # registerAllTools
    meta/                    # ping, list_connections
    sql/                     # query, begin_transaction, commit, rollback, execute

Read the full file on GitHub · 119 lines

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.

  1. 3d ago First seen · 119 lines · 1,616 tokens per session scan A 6e5d65fc2946

Subscribe to this mod's changes

postgres-mcp-server CLAUDE.md is an instructions file published in the GitHub repository arieffian/postgres-mcp-server (0 stars, last pushed 28d ago), licensed MIT. It adds 1,616 tokens to every session, about $0.0081 per session on Opus 5. 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens