n8n-code-tool

n8n-code-tool is a skill for Claude Code, Codex from czlonkowski/n8n-mcp. It costs 221 tokens per session (4,140 once invoked), scanned A, original, MIT.

A guide to the n8n Custom Code Tool, a code-based tool that an AI agent can call during a workflow. It explains how this differs from the regular Code node, including its input and output rules.

In plain words
What is it for?
Writing JavaScript or Python that an AI agent invokes, reading the agent's query, defining input data, and returning a text result.
Why use it?
It prevents developers from treating an agent tool like a normal workflow step, which can cause failures involving inputs, return values, or unavailable helpers. It clarifies what the tool sandbox supports.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Writing JavaScript or Python that an AI agent invokes, reading the agent's…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/czlonkowski/n8n-mcp/n8n-code-tool
About the project

n8n-MCP is a Model Context Protocol server that gives AI assistants structured knowledge of n8n's workflow-automation nodes, including their properties, operations, documentation, and examples. It helps developers use AI assistants to create and work with n8n workflows. The catalogue contains skills, agents, and instructions for using it.

czlonkowski/n8n-mcp · 22,842 stars · on GitHub · n8n-mcp.com

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.

Any agent
npx skills add czlonkowski/n8n-mcp --skill n8n-code-tool
Clone the repo
git clone --depth 1 https://github.com/czlonkowski/n8n-mcp

Made for: Claude Code, Codex.

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-code-tool

README.md
[![agentmods](https://agentmods.dev/badge/skills/czlonkowski/n8n-mcp/n8n-code-tool.svg)](https://agentmods.dev/skills/czlonkowski/n8n-mcp/n8n-code-tool)
Your own site
<a href="https://agentmods.dev/skills/czlonkowski/n8n-mcp/n8n-code-tool"><img src="https://agentmods.dev/badge/skills/czlonkowski/n8n-mcp/n8n-code-tool.svg" alt="Measured on agentmods" height="20"></a>
Per session 221 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,140 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00221 $0.04140
Opus 5 $0.00111 $0.02070
Sonnet 5 $0.00044 $0.00828
Haiku 4.5 $0.00022 $0.00414

Measured 7d ago against content hash 57b3b0d3a222, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

n8n-code-tool 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 7d 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.

Origin

Copies of this mod

4 near-identical copies found in the catalogue:

data/skills/n8n-code-tool/SKILL.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

n8n Custom Code Tool

Expert guidance for writing code inside @n8n/n8n-nodes-langchain.toolCode — the tool an AI Agent can invoke, not the regular workflow Code node.


⚠️ This is NOT the Code node

The Custom Code Tool looks like a Code node in the editor — same JavaScript editor, similar layout — but it is a completely different node from a different package with a different runtime contract.

Code node Custom Code Tool
Node type n8n-nodes-base.code @n8n/n8n-nodes-langchain.toolCode
Package n8n-nodes-base @n8n/n8n-nodes-langchain
Invoked by Previous node (workflow flow) AI Agent (LangChain)
Input $input.all() — item stream query — string or object from LLM
Return [{json: {...}}] (items array) A string
$fromAI() N/A Not available (see Errors)
HTTP helper this.helpers.httpRequest (auth helpers blocked) Not exposed to the tool sandbox
State Per-run execution data No getContext, no $getWorkflowStaticData

If you treat it like a Code node, it fails. The rest of this skill covers the Code Tool's actual contract.


Quick Start

Minimal JavaScript Code Tool

// `query` is whatever the AI sent (a string by default)
return `You asked: ${query}`;

Minimal Python Code Tool

# `_query` is whatever the AI sent (a string by default)
return f"You asked: {_query}"

Essential Rules

  1. Return a string. Numbers are auto-converted. Anything else throws "The response property should be a string, but it is an object".
  2. Input variable is fixed: query (JS), _query (Python). You cannot rename it.
  3. Do NOT use $fromAI() inside the Code Tool sandbox — it throws "No execution data available".
  4. Do NOT use [{json: {...}}] return format — that's for Code nodes. Throws "Wrong output type returned".
  5. Use a descriptive tool name (letters/numbers/underscores, v1.1+). The agent calls the tool by its name.
  6. Write a precise description — the LLM decides whether to invoke the tool based on it.

Read the full file on GitHub · 339 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 339 lines · 221 tokens per session scan A 57b3b0d3a222

Subscribe to this mod's changes

n8n-code-tool is a skill published in the GitHub repository czlonkowski/n8n-mcp (22,842 stars, last pushed 3d ago), licensed MIT. It adds 221 tokens to every session and 4,140 once invoked, about $0.0011 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 2026-08-30.