mcptesting

Rules for testing an MCP server that provides tools for the ethers-v6 Ethereum library. Ethereum is a blockchain platform, and ethers-v6 is a JavaScript library for using it.

In plain words
What is it for?
Keeping MCP server tests focused, avoiding command-line execution of servers, preventing console output that could break communication, and avoiding creation of unrelated servers.
Why use it?
They prevent testing methods that do not work with MCP servers and protect the standard input/output communication channel.

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/dennisonbertram/mcp-ethers-v6/mcptesting
Clone the repo
git clone --depth 1 https://github.com/dennisonbertram/mcp-ethers-v6

Made for: Cursor.

Per session 69 This file is loaded in full into every session.
When invoked 69 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00069 $0.00069
Opus 5 $0.00034 $0.00034
Sonnet 5 $0.00014 $0.00014
Haiku 4.5 $0.00007 $0.00007

Measured 2d ago against content hash 7fc2786b6733, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcptesting 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.

Origin

This is a copy

100% identical to mcptesting — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/rules/mcptesting.mdc · 12 lines

What it actually says

MCP Server testing

  • Do not run MCP servers at the command line, they don't return anything and can not be tested this way
  • Do not use console.log in MCP servers. They break STDIO interface
  • Stay focused
  • Do not create new servers
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 · 12 lines · 69 tokens per session scan A 7fc2786b6733

Subscribe to this mod's changes

mcptesting is a cursor rule published in the GitHub repository dennisonbertram/mcp-ethers-v6 (1 stars, last pushed 1y ago), licensed MIT. It adds 69 tokens to every session, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to mcptesting, differing in 0 lines, and is treated as a copy.