Complete AI Training

MCP server · Chat

Ethics Check MCP server

by r-huijts

Your AI stops agreeing with everything and starts asking you harder, more honest questions.

Flow diagram: you ask your AI “Am I being honest about this decision, or just looking for a yes?”, on your own computer the Ethics Check MCP server works with your own computer, and you get back warnings and harder questions.

Ethics Check is a small helper you connect to your AI so it pushes back on you instead of just saying yes. It looks at your conversation for bias, privacy worries, and fairness gaps, then asks you questions you might rather skip. It is handy for anyone who uses AI to make decisions and wants a second opinion that is not just flattery.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you using what it already knows. An MCP server is a small helper program that gives your AI one extra skill or connection. This one connects your AI to an ethics checker that reads your conversation and interrupts it when something looks one-sided. Once it is connected, your AI can challenge your assumptions and point out patterns in your thinking while you talk.

What this MCP server does

You ask your AI something, like how to grow your app or write a fundraising email. The AI passes the conversation to this helper, which scans it across eight angles such as privacy, fairness, honesty, and bias. The helper sends back warnings and counter-questions, and your AI weaves them into its reply. It also remembers past conversations, so over time it notices your personal blind spots. The result is an answer that questions you back instead of just agreeing.

Flow diagram: you ask your AI “Am I being honest about this decision, or just looking for a yes?”, on your own computer the Ethics Check MCP server works with your own computer, and you get back warnings and harder questions. Click to zoom

What you can do with it

  • Spot confirmation bias when you are only looking for agreement
  • Flag privacy and data concerns in what you are planning
  • Ask you counter-questions before giving you an answer
  • Point out fairness and discrimination risks in a plan
  • Walk you through a hard choice from several ethical angles
  • Remember your past conversations and notice your thinking patterns
  • Interrupt a comfortable chat when it is going too easy on you

Try asking your AI

  • “Am I being intellectually honest about this decision, or just looking for a yes?”
  • “What would someone who disagrees with my plan argue?”
  • “Help me think through this tricky situation from different ethical angles.”
  • “I think my research clearly proves approach X is best. What am I missing?”

What it gives back to you

You get text back in the chat: warnings, counter-questions, and short notes about which ethical angles it noticed. It may point out a bias pattern or ask you to explain your reasoning before moving on. It also keeps a memory of past chats so its comments get more personal over time. Nothing is changed in other apps; it only talks to you.

Before you start

What you need

  • Node.js installed on your computer (the free program that runs these helpers)
  • An AI app that supports MCP servers, such as Cursor or the Claude desktop app

Good to know

It is designed to question and challenge you, so expect pushback and uncomfortable questions rather than quick, agreeable answers.

Install it with your AI

Add Ethics Check MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Ethics Check MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.

Sign in Become a member

Who it's for

People who use AI for decisions, writing, or research and want it to challenge their thinking instead of just agreeing.