n8n-mcp-server: Instructions file for Claude Code

CLAUDE.md

n8n-mcp-server CLAUDE.md is an instructions file for Claude Code from masseater/n8n-mcp-server. It costs 8,993 tokens per session, scanned A, original, MIT.

A set of project instructions for developing and maintaining an n8n MySQL MCP server with Claude Code. It documents dependency installation, development, building, checks, testing, and production commands.

In plain words
What is it for?
Use it when installing dependencies, starting development servers, building TypeScript, checking types, linting, finding unused code, running tests, or starting the compiled server.
Why use it?
It gives contributors a shared reference for running the project and checking changes correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is masseater/n8n-mcp-server's own configuration. It tells Claude Code how to work on n8n-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 n8n-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to masseater/n8n-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/masseater/n8n-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/masseater/n8n-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 n8n-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/masseater/n8n-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/masseater/n8n-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/masseater/n8n-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/masseater/n8n-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 n8n-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/masseater/n8n-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/masseater/n8n-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,993 This file is loaded in full into every session.
When invoked 8,993 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 $0.08993 $0.08993
Opus 5 $0.04496 $0.04496
Sonnet 5 $0.01799 $0.01799
Haiku 4.5 $0.00899 $0.00899

Measured 9d ago against content hash 9b2bd497e89c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

n8n-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 9d 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 · 1,077 lines

How it starts

The opening of the file, as written. The whole thing — 1,077 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.

Development Commands

# Install dependencies (using pnpm)
pnpm install

# Development with auto-reload
pnpm run dev          # stdio transport (default)
pnpm run dev:http     # HTTP transport on port 3000

# Build
pnpm run build        # Compile TypeScript to dist/
pnpm run clean        # Remove dist/ directory

# Type checking & Linting
pnpm run type-check   # Run TypeScript compiler without emitting
pnpm run lint         # Run ESLint
pnpm run lint:fix     # Fix ESLint errors automatically

# Code Quality
pnpm run knip         # Detect unused files, dependencies, exports
pnpm run knip:fix     # Auto-fix knip issues

# Testing
pnpm run test         # Run tests once
pnpm run test:watch   # Run tests in watch mode
pnpm run test:coverage # Run tests with coverage

# Production
pnpm start            # Run built code with stdio transport
pnpm start:http       # Run built code with HTTP transport

Recommended Development Workflow

HTTPモードでバックグラウンド起動を推奨

HTTPモードでバックグラウンド起動すると、コード修正が即座に反映され(HMR)、開発効率が大幅に向上します:

# バックグラウンドでHTTPサーバーを起動
pnpm run dev:http &

# または、別のターミナルで起動
pnpm run dev:http

利点:

  • ファイル変更を検知して自動リロード(tsx --watch)
  • MCPツールの動作確認がリアルタイムで可能
  • ログ出力でツール登録状態を確認可能
  • stdio transportと異なり、複数のクライアントから同時接続可能

Architecture Overview

This is a Model Context Protocol (MCP) server that bridges AI models with n8n workflow automation platform.

Core Architecture

Layer 1: Server Layer (src/server/)

  1. MCPServerImpl (src/server/mcp-server.ts)

    • Main server orchestrator
    • Lifecycle: constructor → initialize() → start() → stop()
    • Manages two transport modes: stdio (default) and HTTP
    • Delegates tool management to ToolRegistry
    • Delegates HTTP handling to HttpTransportHandler
  2. ToolRegistry (src/server/tool-registry.ts)

    • Centralized tool management system
    • Manual tool registration (no auto-discovery for safety)
    • Schema caching for performance (cleared via clearCache())
    • Provides getToolSchemas(), getToolByName(), setupToolHandlers()
    • Tool instances stored in Map<string, Tool>

Read the full file on GitHub · 1,077 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. 9d ago First seen · 1,077 lines · 8,993 tokens per session scan A 9b2bd497e89c

Subscribe to this mod's changes

n8n-mcp-server CLAUDE.md is an instructions file published in the GitHub repository masseater/n8n-mcp-server (0 stars, last pushed 9mo ago), licensed MIT. It adds 8,993 tokens to every session, about $0.0450 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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens