MCP Reflection Tool

A Model Context Protocol (MCP) server that provides a "reflect" tool for AI assistants to create cognitive checkpoints and structured reasoning. This tool helps LLMs maintain context, reflect on their work, and think through complex problems systematically.

Why Use This Tool?

Key Insight: Without explicitly outputting thought processes, no deep thinking occurs. This tool creates mandatory cognitive checkpoints that prevent shortcuts and improve accuracy.

Features

• 🧠 Structured Reasoning: Forces AI assistants to reflect step-by-step through complex problems

• ✅ Task Validation: Creates checkpoints to verify requirements are met

• 📝 Learning Documentation: Captures discoveries and insights during problem-solving

• 🔍 Debugging Aid: Helps work through issues systematically by elimination

• 🎯 Decision Audit Trail: Creates a record of reasoning for important decisions

Installation

Quick Install via NPM

Integration with AI Tools

Claude Code

Add the server using a single command:

This will automatically configure the server in your Claude Code settings. After running the command, restart Claude Code completely.

Cursor

Add to your Cursor configuration:

Option 1: Via Settings UI

1. Open Cursor Settings (Cmd/Ctrl + ,)

2. Search for "MCP" or navigate to Features > MCP

3. Add the reflection tool configuration

Option 2: Direct Config Edit

Edit ~/.cursor/mcp_config.json:

Restart Cursor after making changes.

Windsurf

Add to your Windsurf MCP configuration:

Location: ~/.windsurf/mcp.json (macOS/Linux) or %USERPROFILE%\.windsurf\mcp.json (Windows)

Restart Windsurf to apply changes.

Cline (VS Code Extension)

Option 1: Via VS Code Settings UI

1. Open VS Code Settings (Cmd/Ctrl + ,)

2. Search for "Cline MCP"

3. Add server configuration

Option 2: Edit settings.json

Add to your VS Code settings.json:

Reload VS Code window after configuration.

Alternative: Manual Server Mode

The server runs via stdio by default. If you need HTTP mode, use environment variables:

Most modern AI tools support stdio mode automatically.

Usage Examples

Once installed, the AI assistant will have access to the reflect tool. Here are examples of how it gets used:

Before Complex Actions

After Completing Tasks

During Problem Solving

When the Tool Gets Used

The AI assistant will automatically use this tool as a cognitive scratchpad for:

• 🔍 Chain-of-thought reasoning through complex problems

• 📋 Planning your approach before taking actions

• ✅ Reflecting on outcomes after completing tasks

• ✔️ Validating that requirements are met

• 📝 Documenting discoveries and learnings

• 🎯 Creating cognitive checkpoints you can't skip

This helps the AI think step-by-step, improving accuracy and compliance.

Development

Prerequisites

• Node.js 18+ or Bun runtime

• npm or bun package manager

Setup

Building from Source

Project Structure

Configuration

Environment Variables

• PORT: Server port (default: 8080)

  PORT=3000 npx mcp-reflection-tool

How It Works

The reflection tool implements the Model Context Protocol (MCP) to provide a standardized way for AI assistants to access external tools. When an AI assistant needs to reflect on a problem:

1. The AI calls the reflect tool with its reasoning

2. The tool logs the thought process to the server console

3. The tool acknowledges the checkpoint back to the AI

4. This creates a cognitive checkpoint that improves reasoning quality

This "thinking out loud" effect has been shown to significantly improve the accuracy and completeness of AI responses.

Troubleshooting

Common Issues

Port Already in Use

Permission Denied

Tool Not Available in AI Assistant

1. Ensure the MCP server is running

2. Restart your AI tool after adding configuration

3. Check for valid JSON syntax in config files

4. Verify the config file location for your OS

Checking Logs

• Server logs: Visible in terminal where server is running

• Claude Code logs: ~/Library/Logs/Claude/mcp*.log (macOS)

• VS Code logs: View > Output > Select "Cline" from dropdown

• Cursor logs: Help > Toggle Developer Tools > Console

Verifying Installation

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository

2. Create your feature branch (git checkout -b feature/amazing-feature)

3. Commit your changes (git commit -m 'Add amazing feature')

4. Push to the branch (git push origin feature/amazing-feature)

5. Open a Pull Request

License

MIT License - see the LICENSE file for details.

Author

Created as an MCP implementation for enhancing AI reasoning capabilities.

Links

• NPM Package

• GitHub Repository

• Model Context Protocol Docs

• Report Issues

Acknowledgments

• Built with FastMCP framework

• Implements the Model Context Protocol standard

• Inspired by research on structured reasoning for AI systems