neondatabase/mcp-server-neon is a remote Model Context Protocol server that connects AI assistants to Neon’s Postgres database management API. Users can manage databases, create projects and branches, run queries, and perform migrations through natural-language requests. The catalogue entries are instructions and skills for operating Neon through this server.
Borrowing it
Nothing to install: this file belongs to neondatabase/mcp-server-neon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/neondatabase/mcp-server-neon/main/AGENTS.mdgit clone --depth 1 https://github.com/neondatabase/mcp-server-neonWrote 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.
[](https://agentmods.dev/instructions/neondatabase/mcp-server-neon/agents-md)<a href="https://agentmods.dev/instructions/neondatabase/mcp-server-neon/agents-md"><img src="https://agentmods.dev/badge/instructions/neondatabase/mcp-server-neon/agents-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.
<a href="https://agentmods.dev/instructions/neondatabase/mcp-server-neon/agents-md"><img src="https://agentmods.dev/badge/instructions/neondatabase/mcp-server-neon/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.07019 | $0.07019 |
| Opus 5.5 | $0.02808 | $0.02808 |
| Sonnet 5.5 | $0.01404 | $0.01404 |
| Haiku 4.5 | $0.00702 | $0.00702 |
Grade A, and why
mcp-server-neon AGENTS.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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI agents when working with code in this repository.
Project Overview
This is the Neon MCP Server - a Model Context Protocol server that bridges natural language requests to the Neon API, enabling LLMs to manage Lakebase Postgres databases on Neon through conversational commands. The project implements a stateless Streamable HTTP transport with OAuth authentication support.
Architecture Note: The project is a Next.js application at the repository root, deployed on Vercel serverless infrastructure and accessible at mcp.neon.tech.
Development Commands
All commands should be run from the repository root. The project uses pnpm as the package manager, pinned via Corepack. Run corepack enable to activate it.
Troubleshooting: If
pnpm installfails with registry or network errors, check whether your npm registry is configured to use the Databricks proxy. Set the registry in~/.npmrcor.npmrc.
Building and Running
pnpm install
# Start the Next.js dev server (for the remote MCP server)
pnpm dev
Formatting, Linting, and Type Checking
# Check formatting (runs in CI)
pnpm fmt:check
# Auto-fix formatting
pnpm fmt
# Lint
pnpm lint
# Auto-fix lint + formatting together
pnpm lint:fix
# Type check
pnpm typecheck
# Check for unused code and dependencies
pnpm knip
# Auto-fix unused exports/dependencies
pnpm knip:fix
Testing
# Run full test suite (unit + integration + e2e; used in CI)
pnpm test
# Run unit tests
pnpm test:unit
# Run integration tests
pnpm test:integration
# Run MCP protocol e2e tests (real tool calls over MCP protocol)
pnpm test:e2e:mcp
# Run live MCP → Neon E2E tests (requires .env.test)
pnpm test:e2e:live
# Run website e2e tests (Playwright; provisions/validates ephemeral DB first)
pnpm test:e2e:web
# Run all e2e tests
pnpm test:e2e
Live MCP → Neon E2E tests
pnpm test:e2e:live runs a real MCP client and server over the SDK's in-memory
transport, while every tool call reaches the real Neon Management API and a real
temporary Neon database. This is more deterministic than starting an HTTP server
and shelling through mcporter, while still covering MCP schemas, tool
registration, handlers, @neon/sdk, connection-string resolution, and SQL.
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.
- today Changed · +4 lines · +131 tokens per session 0d3f093a4c34
- yesterday Changed · +74 tokens per session 3ac2b18af14f
- 3d ago Changed · -1 lines · +87 tokens per session 1e4abf2c747d
- 6d ago Changed · +1 lines · +127 tokens per session 5a739726ce02
- 17d ago Changed · -5 lines · -36 tokens per session 05e615c5d030
- 22d ago Changed · +34 tokens per session 6e3142f6e505
- 24d ago Changed · +4 lines · +208 tokens per session 5401ebb2c652
- 1mo ago Changed · +32 tokens per session e63518b63368
- 1mo ago Changed · -2 lines · -26 tokens per session beceaf23a56f
- 1mo ago First seen · 509 lines · 6,388 tokens per session scan A 067be79be2d2
mcp-server-neon AGENTS.md is an instructions file published in the GitHub repository neondatabase/mcp-server-neon (663 stars, last pushed yesterday), licensed MIT. It adds 7,019 tokens to every session, about $0.0281 per session on Opus 5.5. 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 2026-08-30.
mcp-server-neon AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-server-neon AGENTS.mdneondatabase/mcp-server-neon | Instructions file | 663 | yesterday | MIT | A | 7,019 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |