n8n-mcp-agent: Instructions file for Claude Code

CLAUDE.md

n8n-mcp-agent CLAUDE.md is an instructions file for Claude Code from anatolykoptev/n8n-mcp-agent. It costs 557 tokens per session, scanned A, original, MIT.

Project-specific instructions for coding agents working on an n8n integration. n8n is a workflow automation tool, and this project exposes its API through an MCP server, a standard way for AI assistants to use tools.

In plain words
What is it for?
Use it when modifying the TypeScript MCP server, its n8n API clients, tools, schemas, handlers, agents, or skills.
Why use it?
It helps an agent understand the repository layout, required documents, configuration switches, and rules that are easy to break. This reduces changes that conflict with the project's design.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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-agent CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/anatolykoptev/n8n-mcp-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/anatolykoptev/n8n-mcp-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 557 This file is loaded in full into every session.
When invoked 557 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 $0.00557 $0.00557
Opus 5.5 $0.00223 $0.00223
Sonnet 5.5 $0.00111 $0.00111
Haiku 4.5 $0.00056 $0.00056

Measured 5d ago against content hash daa52815b805, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

n8n-mcp-agent 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 5d 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 · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

n8n-mcp-agent — notes for coding agents

TypeScript MCP server (@anatolykoptev/n8n-mcp-agent, Node 18+, ESM) that exposes the n8n public API as tools, plus credential factories, execution and workflow helpers, a searchable workflow-template database and sub-agent/skill prompts. User-facing overview in README.md; coding rules in DEVELOPMENT.md; every document is listed in docs/INDEX.md.

Layout

  • src/main.ts entry point (stdio MCP server, auto-connects from N8N_URL and N8N_API_KEY); src/clients/ n8n and patterns HTTP clients with retry; src/tools/ tool definitions; src/handlers/ handlers and the registry that decides which tools are enabled (N8N_ENTERPRISE, N8N_USERS, N8N_FULL); src/schemas/ zod schemas; src/errors/, src/constants/, src/utils/.
  • agents/ and skills/ are shipped in the npm package (files in package.json); extension/ is a separate Chrome extension plus the embedded auth server for session cookies and is not part of the package.
  • N8N_API.yml is the endpoint reference: check it before adding or changing a call. LLM_GUIDE.md and TYPEKIT_MCP_SDK.md are vendored reference copies of MCP docs.

Gate

There is no CI workflow; run locally before a pull request:

npm run lint     # tsc --noEmit
npm test         # vitest run (205 tests)
npm run build    # tsc && chmod +x build/main.js

Invariants easy to break

  • Tool arguments are compact single-line JSON and every tool takes a clientId; active on a workflow is read-only.
  • Enterprise-only tools (projects, variables) and user management stay behind their environment flags; the default set is the 35 core tools.
  • Keep documentation to what is implemented; no public roadmap (DEVELOPMENT.md).
  • Never log or commit API keys or session cookies; .env is ignored, .env.example documents names only. Test fixtures use documentation or private addresses, except the RFC 1918 boundary cases in src/__tests__/schemas.test.ts.
  • New modules follow the @module / @ai-rule header convention used across src/.

Read the full file on GitHub · 43 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. 5d ago First seen · 43 lines · 557 tokens per session scan A daa52815b805

Subscribe to this mod's changes

n8n-mcp-agent CLAUDE.md is an instructions file published in the GitHub repository anatolykoptev/n8n-mcp-agent (0 stars, last pushed 6d ago), licensed MIT. It adds 557 tokens to every session, about $0.0022 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 2026-11-12.

Related

n8n-mcp-agent CLAUDE.md compared with instructions from other repositories

n8n-mcp-agent CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
n8n-mcp-agent CLAUDE.mdanatolykoptev/n8n-mcp-agentInstructions file06d agoMITA557Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot