test

A set of coding rules for building and testing local MCP servers, which let AI assistants connect to tools. It covers connection instructions, tool schemas, file organization, environment secrets, and tests, including tests for calls to n8n.

In plain words
What is it for?
Testing an MCP server with mcp-remote, documenting how to connect to it, organizing API files, and writing unit tests for n8n calls.
Why use it?
It gives a checklist for checking that an MCP server exposes usable tools, supports the required connection method, and does not accidentally expose secrets.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/sonnd08/n8n-mcp/test
Clone the repo
git clone --depth 1 https://github.com/sonnd08/n8n-mcp

Made for: Cursor.

Per session 229 This file is loaded in full into every session.
When invoked 229 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00229 $0.00229
Opus 5 $0.00114 $0.00114
Sonnet 5 $0.00046 $0.00046
Haiku 4.5 $0.00023 $0.00023

Measured 2d ago against content hash 004b2831893d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test 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 2d 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.

.cursor/rules/test.mdc · 19 lines

What it actually says

  • When update or create something, always think about solutions for testing to make sure generated code working well
  • MCP server must support sse
  • using mcp-remote and mcp-remote-client to test mcp server and list tools before confirm that new changes working
npx -p mcp-remote mcp-remote-client http://localhost:3001/mcp
  • Must write down connect instruction when server start
  • Using docs from https://modelcontextprotocol.io/docs/concepts/transports to implement mcp server
  • make sure we do not leak any sensitive env to files that not in .gitignore
  • Always using index.js as entrypoint
  • All tools must have an inputSchema property
  • When testing locally, need to check if .env have needed env or not, it not need to use Authorization header to authorize request to mcp server.
  • Each tools/Api should be splited into a separated file
  • Each API call to n8n should have a unit test
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. 2d ago First seen · 19 lines · 229 tokens per session scan A 004b2831893d

Subscribe to this mod's changes

test is a cursor rule published in the GitHub repository sonnd08/n8n-mcp (3 stars, last pushed 12d ago), licensed MIT. It adds 229 tokens to every session, 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 2026-08-31.