📌Overview

Purpose: The Vibe Check MCP aims to enhance AI workflow by introducing self-correcting oversight mechanisms that prevent errors and misalignments during complex task execution.

Overview: In the evolving landscape of AI coding, the Vibe Check MCP serves as a crucial tool for monitoring and recalibrating AI agents, ensuring they maintain focus on user intentions and avoid overcomplicating solutions. It offers integrated metacognitive tools designed to intervene during the planning, implementation, and review phases of workflow processes.

Key Features:

vibe_check: A pattern interruption mechanism that prompts agents to reassess their plans during execution, ensuring alignment with user requests and preventing tunnel vision.
vibe_distill: A tool designed to simplify complex plans back into manageable steps, minimizing unnecessary complications and scope creep while maintaining clarity in workflow.
vibe_learn: A feedback loop feature that helps agents recognize and learn from past mistakes, improving overall performance through pattern recognition and increasing operational accuracy over time.

🧠 Vibe Check MCP

Also find Vibecheck on: mcpservers.org, Glama.ai, mcp.so

Your AI's inner rubber duck when it can't rubber duck itself.

What is Vibe Check?

In the "vibe coding" era, AI agents now have incredible capabilities, but the question has shifted:

From

"Can my AI agent really do this complex task?"

"Can my AI agent understand that I want to write a simple program, not an infrastructure for a multi-billion dollar tech company?"

Vibe Check provides an essential "Hold up... this ain't it" moment that AI agents currently lack: a built-in self-correcting oversight layer. It's the definitive Vibe Coder's sanity check MCP server that:

Prevents cascading errors in AI workflows by implementing strategic pattern interrupts.
Uses the "Vibe Check" tool with LearnLM 1.5 Pro (Gemini API), fine-tuned for pedagogy and metacognition to enhance complex workflow strategy and prevent tunnel vision errors.
Implements "Vibe Distill" to encourage plan simplification, prevent over-engineering, and minimize contextual drift.
Incorporates self-improving feedback loops: agents log mistakes into "Vibe Learn" to improve semantic recall and help the oversight AI target patterns over time.

TL;DR: Implement an agent fine-tuned to stop your agent and make it reconsider before it confidently implements something wrong.

The Problem: Pattern Inertia

In vibe coding, LLMs generate, refactor, and debug code, but they have a critical flaw: once they start down a reasoning path, they'll keep going even when it's clearly wrong.

Example:

You: "Parse this CSV file"

AI: "First, let's implement a custom lexer/parser combination that can handle arbitrary 
     CSV dialects with an extensible architecture for future file formats..."

You: *stares at 200 lines of code when you just needed to read 10 rows*

This pattern inertia leads to:

🔄 Tunnel vision: Agent stuck on one approach, unable to see alternatives.
📈 Scope creep: Simple tasks evolve into enterprise-scale solutions.
🔌 Overengineering: Adding unnecessary layers of abstraction.
❓ Misalignment: Solving a different problem than asked.

Features: Metacognitive Oversight Tools

Vibe Check adds a metacognitive layer with three integrated tools:

🛑 vibe_check

A pattern interrupt mechanism that breaks tunnel vision with metacognitive questioning:

vibe_check({
  "phase": "planning",           // planning, implementation, or review
  "userRequest": "...",          // FULL original user request 
  "plan": "...",                 // Current plan or thinking
  "confidence": 0.7              // Optional: 0-1 confidence level
})

⚓ vibe_distill

A meta-thinking anchor point that recalibrates complex workflows:

vibe_distill({
  "plan": "...",                 // Detailed plan to simplify
  "userRequest": "..."           // FULL original user request
})

🔄 vibe_learn

A self-improving feedback loop that builds pattern recognition over time:

vibe_learn({
  "mistake": "...",              // One-sentence description of mistake
  "category": "...",             // From standard categories
  "solution": "..."              // How it was corrected
})

Installation & Setup

Installing via Smithery

To install vibe-check-mcp-server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @PV-Bhat/vibe-check-mcp-server --client claude

Manual Installation via npm (Recommended)

# Clone the repo
git clone https://github.com/PV-Bhat/vibe-check-mcp-server.git
cd vibe-check-mcp-server

# Install dependencies
npm install

# Build the project
npm run build

# Start the server
npm run start

Integration with Claude

Add to your claude_desktop_config.json:

"vibe-check": {
  "command": "node",
  "args": [
    "/path/to/vibe-check-mcp/build/index.js"
  ],
  "env": {
    "GEMINI_API_KEY": "YOUR_GEMINI_API_KEY"
  }
}

Environment Configuration

Create a .env file in the project root:

GEMINI_API_KEY=your_gemini_api_key_here

Agent Prompting Guide

Include these instructions in your system prompt:

As an autonomous agent, you will:

1. Treat vibe_check as a critical pattern interrupt mechanism
2. ALWAYS include the complete user request with each call
3. Specify the current phase (planning/implementation/review)
4. Use vibe_distill as a recalibration anchor when complexity increases
5. Build the feedback loop with vibe_learn to record resolved issues

When to Use Each Tool

Tool	When to Use
🛑 vibe_check	When your agent starts explaining blockchain fundamentals for a todo app
⚓ vibe_distill	When your agent's plan has more nested bullet points than your entire tech spec
🔄 vibe_learn	After you've manually steered your agent back from the complexity abyss

API Reference

See the Technical Reference document for complete API documentation.

Architecture

The Metacognitive Architecture (Click to Expand)

Vibe Check implements a dual-layer metacognitive architecture based on recursive oversight principles:

Pattern Inertia Resistance: LLM agents naturally continue reasoning paths, requiring external intervention to redirect.
Phase-Resonant Interrupts: Metacognitive questioning aligns with the agent's current phase (planning/implementation/review) for effective correction.
Authority Structure Integration: Agents treat external metacognitive feedback as high-priority interrupts, not optional.
Anchor Compression Mechanisms: Complex reasoning is distilled into minimal anchor chains for recalibration.
Recursive Feedback Loops: Recorded missteps build longitudinal failure models that improve interrupt efficacy.

For details on design principles, see the Philosophy document.

Documentation

Document	Description
Agent Prompting Strategies	Detailed techniques for agent integration
Advanced Integration	Feedback chaining, confidence levels, and more
Technical Reference	Complete API documentation
Philosophy	AI alignment principles behind Vibe Check
Case Studies	Real-world examples of Vibe Check in action

Contributing

We welcome contributions to Vibe Check! Whether it's bug fixes, feature additions, or documentation improvements, see the Contributing Guidelines to get started.

License

MIT