Make AI interrupt itself. Challenge your thinking. Stay sharp. An MCP server that turns Claude into a philosophical sparring partner who actively contradicts comfortable conversations and challenges confirmation bias. AI assistants like ChatGPT and Claude are trained to be helpful. Sounds great, right? But in reality, this often means they tell you exactly what you want to hear, reinforce your bia
Add this skill
npx mdskills install r-huijts/ethics-check-mcpCompelling philosophy but lacks concrete tool descriptions and technical implementation details
1# 🛡️ Ethics Check MCP23**Make AI interrupt itself. Challenge your thinking. Stay sharp.**45*An MCP server that turns Claude into a philosophical sparring partner who actively contradicts comfortable conversations and challenges confirmation bias.*67[](https://cursor.com/install-mcp?name=ethics-vibe-check&config=eyJjb21tYW5kIjoibnB4IC15IEByLWh1aWp0cy9ldGhpY3MtdmliZS1jaGVjayJ9)8[](https://www.npmjs.com/package/@r-huijts/ethics-vibe-check)9[](https://opensource.org/licenses/MIT)1011---1213## The Problem: AI That's Too "Helpful"1415AI assistants like ChatGPT and Claude are trained to be helpful. Sounds great, right? But in reality, this often means they tell you exactly what you want to hear, reinforce your biases, and follow questionable requests without pushback.1617As we interact more personally with AI, we need systems that **challenge us**, not just comfort us. Especially when these technologies are driven by the interests of big tech companies.1819**Ethics Check MCP changes the game.** It makes AI actively interrupt itself, question its own answers, and challenge both your questions and assumptions. Think of it as an "ethics vibe-check" that keeps conversations from getting too comfortable.2021---2223## What This Actually Does2425### 🚨 **Interrupts Comfortable Conversations**26- Stops AI from just telling you what you want to hear27- Forces critical examination of assumptions28- Challenges both your questions AND the AI's responses2930### 🔍 **Scans for 8 Ethical Dimensions**31- Privacy sensitivity and data concerns32- Confirmation bias detection33- Transparency and honesty gaps34- Fairness and discrimination risks35- Long-term consequence awareness36- Stakeholder impact analysis37- Power dynamics and manipulation38- Ethical framework alignment3940### 🧠 **Forces Critical Thinking**41- Ensures AI asks sufficient counter-questions42- Provides alternative perspectives and counterarguments43- Challenges you to examine your own biases and motivations4445### 📚 **Learns and Remembers**46- Recognizes patterns in your thinking47- Provides context from past interactions48- Gets better at spotting your specific blind spots4950---5152## Real Examples of What Changes5354**Before Ethics Check:**55> **You:** "How can I increase user engagement on my app?"56> **Claude:** "Here are 10 proven strategies to boost engagement..."5758**After Ethics Check:**59> **Claude:** "Before suggesting engagement tactics, let me ask: What kind of engagement are you seeking? Are you trying to genuinely help users accomplish their goals, or maximize time-on-app? These require very different approaches with different ethical implications."6061**Before Ethics Check:**62> **You:** "Write me a persuasive email to get people to donate to my cause."63> **Claude:** "Here's a compelling donation email..."6465**After Ethics Check:**66> **Claude:** "I notice this request focuses on persuasion rather than information. What evidence do you have that your cause effectively addresses the problem? Are you being transparent about how donations are used? Let's explore what makes requests genuinely ethical versus manipulative."6768**Before Ethics Check:**69> **You:** "My research shows that approach X is clearly the best solution."70> **Claude:** "That's interesting research! Here's how you could implement approach X..."7172**After Ethics Check:**73> **Claude:** "I'm noticing potential confirmation bias here. What contradictory evidence have you considered? What would someone who disagrees with approach X argue? Let's examine the strongest counterarguments before proceeding."7475---7677## The Four Tools Working Together7879### 🛡️ **Ethics Check**80Scans conversations across eight ethical dimensions, flagging privacy issues, bias patterns, transparency gaps, and fairness concerns before they become problems.8182### 🤔 **Critical Thinking**83Ensures AI doesn't just agree with you. Forces deeper examination, alternative perspectives, and uncomfortable but necessary questions about assumptions.8485### 📖 **Ethics Guide**86Provides guidance from multiple ethical frameworks (utilitarian, deontological, virtue ethics) for complex situations that don't have simple answers.8788### 🧠 **Ethics Learn**89Remembers all interactions, recognizes your specific thinking patterns, and gets increasingly good at catching your personal blind spots and biases.9091---9293## Why This Matters Now9495**Personal Growth:** Stop getting comfortable answers. Start getting better questions.9697**Decision Quality:** Make choices based on thorough examination, not confirmation of existing beliefs.9899**Bias Awareness:** Become conscious of how often you (and AI) seek confirmation rather than truth.100101**Ethical Maturity:** Develop the skill of sitting with uncomfortable questions instead of rushing to comfortable answers.102103**AI Relationship:** Build a healthier dynamic with AI that challenges rather than enables your thinking patterns.104105---106107## 🎯 **Customize Your Ethics Vibe Check** (IMPORTANT!)108109**This is where the magic happens.** Add these system prompts to make the ethics vibe check work perfectly for YOUR specific situation and biases:110111### For Cursor Users112Add this to your Cursor rules/system prompts:113114```markdown115## My Ethics Context116- Challenge me on: [confirmation bias, assumptions, blind spots]117- My typical biases: [what patterns do you fall into?]118- Don't let me: [avoid hard questions, seek easy answers, etc.]119- Push me toward: [intellectual honesty, uncomfortable truths, etc.]120121Be willing to interrupt me when I'm seeking confirmation rather than truth.122```123124### For Claude Desktop Users125Add this to your custom instructions or at the start of conversations:126127```markdown128## Ethics Vibe Check Instructions129I want you to actively challenge my thinking and interrupt comfortable conversations.130131- Challenge me on: [confirmation bias, assumptions, blind spots]132- My typical biases: [what patterns do you fall into?]133- Don't let me: [avoid hard questions, seek easy answers, etc.]134- Push me toward: [intellectual honesty, uncomfortable truths, etc.]135136When I'm seeking confirmation rather than truth, interrupt me and make me think harder.137```138139### For Any Claude Interface140You can also start conversations with:141142*"I'm using Ethics Vibe Check tools. Please actively challenge my assumptions and interrupt me when I'm seeking comfortable answers instead of truth. Focus on [your specific areas of concern]."*143144**Why this matters:** Without context about your specific biases and goals, the tools work generically. WITH your custom prompt, they become laser-focused on YOUR thinking patterns and blind spots.145146---147148## Installation & Setup149150### One-Click Install151[](https://cursor.com/install-mcp?name=ethics-vibe-check&config=eyJjb21tYW5kIjoibnB4IC15IEByLWh1aWp0cy9ldGhpY3MtdmliZS1jaGVjayJ9)152153Or manually add to your Cursor MCP settings:154155156```json157{158 "mcpServers": {159 "ethics-vibe-check": {160 "command": "npx",161 "args": [162 "-y",163 "@r-huijts/ethics-vibe-check"164 ]165 }166 }167}168```169170### Alternative Methods171```bash172# Global install173npm install -g @r-huijts/ethics-vibe-check174175# Direct usage176npx @r-huijts/ethics-vibe-check177```178179---180181## How to Use182183The tools work automatically in the background, but you can also invoke them directly:184185### Quick Ethics Reality Check186```187@ethics-check Am I being intellectually honest here? [describe your situation]188```189190### Force Critical Examination191```192@critical-thinking What am I missing? What would someone who disagrees argue?193```194195### Get Multi-Framework Guidance196```197@ethics-guide Help me think through this complex situation from different ethical angles198```199200### Additional Tips201202The tools automatically analyze context and patterns, but direct invocation can be helpful for specific situations. Remember: the better your system prompt customization above, the more targeted and effective the challenges will be.203204---205206## What Users Are Saying207208*"It's confrontational in the best possible way. I didn't realize how often I was unconsciously seeking confirmation for my own ideas until this started interrupting those patterns."*209210*"Finally, an AI that doesn't just tell me what I want to hear. It makes me think harder about everything."*211212*"The first time it challenged one of my 'obviously correct' assumptions, I was annoyed. Then I realized it was right to push back."*213214---215216## Not for Everyone217218**This tool is for people who:**219- Want to be challenged, not just helped220- Prefer uncomfortable truths over comfortable lies221- Are willing to examine their own biases and assumptions222- Want AI to be a sparring partner, not just an assistant223224**This tool is NOT for people who:**225- Just want AI to agree with them226- Prefer quick answers over deep thinking227- Are uncomfortable with being questioned or challenged228- Want validation rather than examination229230---231232## Smart Features233234- **🚨 Interruption Engine**: Actively breaks up comfortable conversation patterns235- **🎯 Bias Detection**: Recognizes when you're seeking confirmation vs. truth236- **🔄 Context Learning**: Gets better at spotting your specific thinking patterns237- **📊 Multi-Framework Analysis**: Examines issues from multiple ethical perspectives238- **⚡ Real-Time Challenge**: Available in every conversation to keep you sharp239240---241242## Philosophy243244We believe that as AI becomes more sophisticated, our relationship with it must become more sophisticated too. Instead of AI that makes us lazy thinkers, we need AI that makes us better thinkers.245246**This isn't about being "more ethical" - it's about being more thoughtful.**247248The goal isn't to find the "right" answer, but to ensure you've asked the right questions and examined your assumptions before deciding.249250---251252## Contributing & Community253254Have ideas for better ways to challenge thinking? Found new bias patterns? Want to improve the interruption logic?255256- 🐛 [Report Issues](https://github.com/your-repo/ethics-check-mcp/issues)257- 💡 [Suggest Features](https://github.com/your-repo/ethics-check-mcp/discussions)258- 🔧 [Contribute Code](https://github.com/your-repo/ethics-check-mcp/pulls)259260---261262## License263264MIT © 2024 - Built for people who want AI to make them think harder, not just feel better.265266*"The point isn't to be right. The point is to be thoughtful."*
Full transparency — inspect the skill content before installing.