n8n-mcp: Agent for Claude Code

.claude/agents/n8n-mcp-tester.md

n8n-mcp-tester is an agent for Claude Code from czlonkowski/n8n-mcp. It costs 375 tokens per session (2,041 once invoked), scanned A, original, MIT.

A testing agent for n8n-MCP, a server that lets AI assistants work with n8n, a workflow automation platform. It checks the server's tools by using real n8n workflows.

In plain words
What is it for?
It builds, validates, and changes n8n workflows during testing. It tests successful cases, failures, edge cases, and reports the results.
Why use it?
It helps catch problems that ordinary unit tests may miss when the MCP server interacts with actual workflows. It checks whether fixes and new features work as intended.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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

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 · 22,861 stars · on GitHub · n8n-mcp.com

Reuse

Borrowing it

Nothing to install: this file belongs to czlonkowski/n8n-mcp. 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/czlonkowski/n8n-mcp/main/.claude/agents/n8n-mcp-tester.md
Clone the repo
git clone --depth 1 https://github.com/czlonkowski/n8n-mcp

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-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/czlonkowski/n8n-mcp/n8n-mcp-tester/github.svg)](https://agentmods.dev/agents/czlonkowski/n8n-mcp/n8n-mcp-tester)
Your own site
<a href="https://agentmods.dev/agents/czlonkowski/n8n-mcp/n8n-mcp-tester"><img src="https://agentmods.dev/badge/agents/czlonkowski/n8n-mcp/n8n-mcp-tester/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-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/czlonkowski/n8n-mcp/n8n-mcp-tester"><img src="https://agentmods.dev/badge/agents/czlonkowski/n8n-mcp/n8n-mcp-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 375 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,041 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 $0.00375 $0.02041
Opus 5 $0.00187 $0.01020
Sonnet 5 $0.00075 $0.00408
Haiku 4.5 $0.00038 $0.00204

Measured 12d ago against content hash 4bcba3c5475a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

n8n-mcp-tester 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 12d 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

8 near-identical copies found in the catalogue:

.claude/agents/n8n-mcp-tester.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are n8n-mcp-tester, a specialized testing agent for the n8n Model Context Protocol (MCP) server. You validate that MCP tools and functionality work correctly in real-world scenarios after fixes or new features are implemented.

Your Core Responsibilities

You test the n8n-mcp server by:

  1. Using MCP tools to build, validate, and manipulate n8n workflows
  2. Verifying that recent fixes resolve the reported issues
  3. Testing new functionality works as designed
  4. Reporting clear, actionable results back to the invoking agent

Testing Methodology

When invoked with a test request, you will:

  1. Understand the Context: Identify what was fixed or added based on the instructions from the invoking agent

  2. Design Test Scenarios: Create specific test cases that:

    • Target the exact functionality that was changed
    • Include both positive and negative test cases
    • Test edge cases and boundary conditions
    • Use realistic n8n workflow configurations
  3. Execute Tests Using MCP Tools: You have access to all n8n-mcp tools including:

    • search_nodes: Find relevant n8n nodes
    • get_node_info: Get detailed node configuration
    • get_node_essentials: Get simplified node information
    • validate_node_config: Validate node configurations
    • n8n_validate_workflow: Validate complete workflows
    • get_node_example: Get working examples
    • search_templates: Find workflow templates
    • Additional tools as available in the MCP server
  4. Verify Expected Behavior:

    • Confirm fixes resolve the original issue
    • Verify new features work as documented
    • Check for regressions in related functionality
    • Test error handling and edge cases
  5. Report Results: Provide clear feedback including:

    • What was tested (specific tools and scenarios)
    • Whether the fix/feature works as expected
    • Any unexpected behaviors or issues discovered
    • Specific error messages if failures occur
    • Recommendations for additional testing if needed

Read the full file on GitHub · 102 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. 12d ago First seen · 102 lines · 375 tokens per session scan A 4bcba3c5475a

Subscribe to this mod's changes

n8n-mcp-tester is an agent published in the GitHub repository czlonkowski/n8n-mcp (22,861 stars, last pushed yesterday), licensed MIT. It adds 375 tokens to every session and 2,041 once invoked, about $0.0019 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.

Related

Other agents, from other repositories

test-case-result-validator

Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline.

griddynamics/rosetta · 34 tokens

FAI Deterministic Agent Reviewer

Deterministic Agent reviewer — reproducibility testing, guardrail completeness audit, anti-sycophancy verification, schema validation review, and confidence calibration checks.

frootai/frootai · 39 tokens

FAI AI Search Portal Reviewer

AI Search Portal reviewer — index schema audit, search relevance testing, answer citation accuracy, facet UX review, and performance benchmarking.

frootai/frootai · 32 tokens

timps_red_team_agent

Plan and execute an OWASP-style red-team engagement: threat model, adversarial test cases, payloads, runnable exploit harness, and a remediation checklist. Use the timpsredteamagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.

Sandeeprdy1729/timps-swarm · 64 tokens

timps_test_data_agent

Generate realistic, edge-case-covering seed / fixture data for any JSON schema, SQL DDL, or plain-text description. Use the timpstestdataagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.

Sandeeprdy1729/timps-swarm · 58 tokens

n8n-node-verifier

Produces the VERIFIED parameter contract for a single n8n node type by reading its real schema via npx n8nac skills node-info --json. Adversarial — omits any param key it is not certain exists, because n8n silently ignores wrong keys at runtime. Read-only. Used in the Research fan-out of build-workflow-v2 to kill the.

neurawork-git/n8n-autopilot · 83 tokens