neon-mcp-server: Instructions file for Claude Code

CLAUDE.md

neon-mcp-server CLAUDE.md is an instructions file for Claude Code from voyagi/neon-mcp-server. It costs 1,366 tokens per session, scanned A, original, MIT.

Development instructions for an MCP server that connects a Neon Postgres database to Claude. Neon is a hosted PostgreSQL database service, and MCP is a way for AI assistants to use external tools and data.

In plain words
What is it for?
Building a demo CRM connection for viewing customers, support tickets, and products, including read and write actions.
Why use it?
It explains how to let Claude ask questions about business data and make database changes without manually writing each query.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is voyagi/neon-mcp-server's own configuration. It tells Claude Code how to work on neon-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything neon-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to voyagi/neon-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/voyagi/neon-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/voyagi/neon-mcp-server

Made for: Claude Code.

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 neon-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/voyagi/neon-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/voyagi/neon-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/voyagi/neon-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/voyagi/neon-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for neon-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/voyagi/neon-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/voyagi/neon-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,366 This file is loaded in full into every session.
When invoked 1,366 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01366 $0.01366
Opus 5 $0.00683 $0.00683
Sonnet 5 $0.00273 $0.00273
Haiku 4.5 $0.00137 $0.00137

Measured 8d ago against content hash 0d1d9af76e75, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

neon-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 8d 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 · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Neon MCP Server — Upwork Portfolio Project

Purpose

Demo project showcasing custom MCP server development for business data integration. Demonstrates building MCP (Model Context Protocol) servers that connect business data to AI assistants like Claude.

What to Build

An MCP server that connects a Neon Postgres database to Claude Desktop/Code, allowing natural language queries against business data.

Demo Scenario: "TechStart CRM"

A fictional small business CRM with:

  • Customers — name, email, company, status
  • Tickets — support tickets linked to customers
  • Products — catalog with pricing

The MCP server exposes this data so Claude can:

  • "Show me all open tickets"
  • "Find customers from Acme Corp"
  • "What's our most expensive product?"
  • "Create a new ticket for John about billing"
  • "How many customers signed up this month?"

Value Proposition

  • MCP is cutting-edge (most freelancers don't know it yet)
  • Shows real database integration, not toy examples
  • Demonstrates both read AND write operations
  • Clients can test it themselves in Claude Desktop

Tech Stack

  • Runtime: Node.js + TypeScript
  • MCP SDK: @modelcontextprotocol/sdk
  • Database: Neon Postgres (@neondatabase/serverless)
  • Validation: Zod
  • Linter/Formatter: Biome
  • Transport: stdio (for Claude Desktop/Code integration)

Architecture

src/
  index.ts              — MCP server entry point + transport setup
  server.ts             — Server definition, tool + resource registration
  tools/
    customers.ts        — CRUD tools for customers table
    tickets.ts          — CRUD tools for tickets table
    products.ts         — Read tools for products table
    analytics.ts        — Aggregate queries (counts, summaries)
  resources/
    schema.ts           — Expose DB schema as MCP resource
  lib/
    db.ts               — Neon database client (sql tagged templates + query helper)
    customers.ts        — Customer lookup/validation helpers
    errors.ts           — PostgreSQL error code helpers
    formatters.ts       — Product price formatting
    responses.ts        — MCP tool response helpers
    validation.ts       — Zod schemas and sanitization
seed/
  schema.sql            — Table definitions
  seed.sql              — Demo data (22 customers, 32 tickets, 12 products)
  run-seed.mjs          — Script to create tables and seed data
  e2e-test.mjs          — E2E tests against live database

Read the full file on GitHub · 195 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. 8d ago First seen · 195 lines · 1,366 tokens per session scan A 0d1d9af76e75

Subscribe to this mod's changes

neon-mcp-server CLAUDE.md is an instructions file published in the GitHub repository voyagi/neon-mcp-server (0 stars, last pushed yesterday), licensed MIT. It adds 1,366 tokens to every session, about $0.0068 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

next.js AGENTS.md

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

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 · 5,153 tokens

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

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

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 · 4,469 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