postgres-mcp-server CLAUDE.md

postgres-mcp-server CLAUDE.md is an instructions file for coding agents from eltonf/postgres-mcp-server. It costs 238 tokens per session, scanned A, original, MIT.

A repository-specific instruction file for a PostgreSQL database connector, describing its structure, design decisions, and development commands.

In plain words
What is it for?
Use it when working on the connector, its database schema inspection, guarded SELECT or WITH queries, MCP handlers, builds, tests, or startup commands.
Why use it?
It gives an agent the context needed to change this codebase consistently and safely, including its read-only database-query rules.

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/eltonf/postgres-mcp-server/claude-md
Clone the repo
git clone --depth 1 https://github.com/eltonf/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/eltonf/postgres-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/eltonf/postgres-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/eltonf/postgres-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/eltonf/postgres-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 238 This file is loaded in full into every session.
When invoked 238 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 $0.00238 $0.00238
Opus 5 $0.00119 $0.00119
Sonnet 5 $0.00048 $0.00048
Haiku 4.5 $0.00024 $0.00024

Measured 2d ago against content hash abdeef1a503d, 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 2d 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 · 31 lines

What it actually says

CLAUDE.md

This repository is postgres-mcp-server, a PostgreSQL-specific MCP server for schema introspection and guarded read-only queries.

Architecture

  • src/index.ts registers MCP tools and starts the stdio server.
  • src/core/* contains reusable code intended for future extraction.
  • src/postgres/* contains PostgreSQL-specific code:
    • pg connection pool
    • identifier helpers
    • information_schema and pg_catalog catalog queries
  • src/handlers/* adapts MCP tool input/output to the PostgreSQL implementation.

Design Notes

  • One MCP server instance connects to one configured PostgreSQL database.
  • DB_SCHEMA defaults to public; tool calls may override schema.
  • execute_query accepts read-only SELECT/WITH queries, validates access control, and enforces LIMIT.
  • Routine/function definition tools are intentionally deferred for v1.

Development Commands

npm run build
npm test
npm start

Use neutral examples such as app_db, customers, orders, products, and order_items.

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. 2d ago First seen · 31 lines · 238 tokens per session scan A abdeef1a503d

Subscribe to this mod's changes

postgres-mcp-server CLAUDE.md is an instructions file published in the GitHub repository eltonf/postgres-mcp-server (0 stars, last pushed 3mo ago), licensed MIT. It adds 238 tokens to every session, about $0.0012 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.