Anti Bullshit MCP Server

🚀 Anti-Bullshit MCP Server

A Model Context Protocol (MCP) server that uses multiple epistemological frameworks to analyze claims, validate sources, and detect manipulation.

🚀 Quick Start

The Anti-Bullshit MCP Server is a powerful tool for detecting and analyzing bullshit. It offers three main tools to help you assess the credibility of claims and sources, and detect manipulation strategies.

✨ Features

The server provides three main tools for detecting and analyzing bullshit:

1. analyze_claim

Analyze claims using multiple epistemological frameworks:

• Empirical Framework

  • Focus on verifiable evidence.
  • Evaluate reproducible results.
  • Reference academic and scientific sources.
  • Assess methodological rigor.

• Responsible Framework

  • Evaluate ethical impacts.
  • Examine community impacts.
  • Consider traditional knowledge.
  • Validate source credibility.

• Harmonious Framework

  • Evaluate coherence with existing knowledge.
  • Integrate multiple perspectives.
  • Consider contextual applicability.
  • Assess systemic impacts.

• Plural Framework

  • Combine all other frameworks.
  • Consider multiple ways of knowing.
  • Evaluate contextual applicability.
  • Assess practical effects.
  • Check alignment with community values.

2. validate_sources

• Extract and analyze cited sources.
• Validate credibility and authority.
• Cross-reference across multiple platforms.
• Assess methodological rigor.
• Check for conflicts of interest.

3. check_manipulation

Detect manipulation strategies, including:

• Emotional manipulation
• Social pressure
• False authority
• Artificial scarcity
• Creation of a sense of urgency

📦 Installation

Prerequisites

• Node.js >= 18.0.0
• npm or yarn

Setup Steps

1. Install dependencies:

npm install

2. Build the server:

npm run build

3. Add to Claude Desktop (MacOS):

{
  "mcpServers": {
    "anti-bullshit": {
      "command": "node",
      "args": ["/path/to/anti-bullshit-mcp-server/build/index.js"]
    }
  }
}

Path: ~/Library/Application Support/Claude/claude_desktop_config.json

Or for the VSCode extension: Path: ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json

💻 Usage Examples

Basic Usage

// Analyze a claim
const result = await analyze_claim({
  text: "Research shows that 87% of experts agree with this controversial view",
  framework: "empirical"
});

// Validate sources
const validation = await validate_sources({
  text: "According to Dr. Smith's groundbreaking research...",
  framework: "responsible"
});

// Check for manipulation
const check = await check_manipulation({
  text: "Act now! This exclusive offer expires in the next 10 minutes!"
});

📚 Documentation

Development Information

Develop with automatic rebuild:

npm run watch

Debug via MCP Inspector:

npm run inspector

Testing Timeline

The server uses January 1, 2025, as a reference date for temporal analysis of claims (especially in relation to philosophical puzzles such as Goodman's "grue" paradox).

📄 License

MIT

👥 Author

Teglon Labs (teglon@vibes.lol)

🤝 Contribution Guidelines

1. Fork the repository.
2. Create a feature branch (git checkout -b feature/amazing-feature).
3. Commit your changes (git commit -am 'Add some amazing feature').
4. Push to the branch (git push origin feature/amazing-feature).
5. Open a Pull Request.