postgres-ssh-mcp CLAUDE.md

postgres-ssh-mcp CLAUDE.md is an instructions file for coding agents from SecretX33/postgres-ssh-mcp. It costs 752 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP server that lets coding assistants inspect PostgreSQL databases, either directly or through an SSH tunnel.

In plain words
What is it for?
Installing dependencies, building, testing individual files, type-checking, formatting, and running the server in development mode.
Why use it?
They give the assistant the project’s commands, structure, coding rules, and tests, so database-related changes can be made consistently and checked.

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/secretx33/postgres-ssh-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/SecretX33/postgres-ssh-mcp

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-ssh-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/secretx33/postgres-ssh-mcp/claude-md.svg)](https://agentmods.dev/instructions/secretx33/postgres-ssh-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/secretx33/postgres-ssh-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/secretx33/postgres-ssh-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 752 This file is loaded in full into every session.
When invoked 752 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 $0.00752 $0.00752
Opus 5 $0.00376 $0.00376
Sonnet 5 $0.00150 $0.00150
Haiku 4.5 $0.00075 $0.00075

Measured 3d ago against content hash cdce6831ec19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

postgres-ssh-mcp 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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

pnpm install          # Install dependencies
pnpm build            # Bundle with tsdown (→ dist/)
pnpm test             # Run all tests (vitest)
pnpm test -- tests/sql-validator.test.ts  # Run a single test file
pnpm typecheck        # Type-check without emitting
pnpm format           # Check formatting (prettier)
pnpm format:write     # Auto-fix formatting
pnpm dev              # Watch mode, rebuild on changes (tsdown)

Architecture

An MCP (Model Context Protocol) server that lets AI tools query PostgreSQL databases, optionally through an SSH tunnel. Runs over stdio transport.

Entrypoint: src/index.ts — loads env, optionally opens an SSH tunnel, creates a pg.Pool, registers MCP tools (run_query, list_schemas, list_tables, describe_table), and connects via StdioServerTransport.

Key modules:

  • config.ts — Zod schema (EnvSchema) for all env vars, SSH config file parser, resolveSshConfig() picks connection mode (direct / SSH config alias / explicit SSH)
  • ssh-tunnel.ts — wraps tunnel-ssh to open an SSH tunnel, returns TunnelInfo with local port
  • database.tspg.Pool creation, query execution helpers. runQuery enforces read-only via BEGIN TRANSACTION READ ONLY + ROLLBACK
  • sql-validator.ts — AST-level query validation using pgsql-parser/@pgsql/traverse. In read-only mode: allowlists SelectStmt/ExplainStmt, walks AST for hidden mutations (CTE DML, SELECT INTO, locking clauses). Always enforces single-statement limit
  • util.ts — reads package.json for project name/version

Three SSH connection modes (determined by env vars):

  1. Direct — no SSH vars → connect to Postgres directly
  2. SSH configSSH_HOST set → parse ~/.ssh/config for that alias
  3. Explicit SSHSSH_HOSTNAME + SSH_USER → use env vars directly

Code Style

  • Prettier with printWidth: 90
  • ESM ("type": "module") — use .js extensions in imports even for .ts files
  • TypeScript strict mode with noUnusedLocals and noUnusedParameters

Read the full file on GitHub · 57 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 · 57 lines · 752 tokens per session scan A cdce6831ec19

Subscribe to this mod's changes

postgres-ssh-mcp CLAUDE.md is an instructions file published in the GitHub repository SecretX33/postgres-ssh-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 752 tokens to every session, about $0.0038 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.