Vibe Check MCP Server is a metacognitive oversight tool for AI agents that prevents pattern inertia and over-engineering in workflows through three key functions:
🛑 Vibe Check: Identifies incorrect assumptions and breaks tunnel vision by asking metacognitive questions during planning, implementation, and review phases.
⚓ Vibe Distill: Simplifies complex plans to prevent over-engineering and keeps workflows aligned with the original user request.
🔄 Vibe Learn: Tracks and categorizes mistakes to build a self-improving feedback loop that prevents recurring errors.
The server integrates with AI agents like Claude, supporting customizable inputs including session management, confidence levels, and detailed thinking logs for precise feedback and improvement.
Enables environment variable configuration through a .env file to store API keys and other configuration values.
Hosted on GitHub with repository access for cloning, contributing, and accessing documentation and case studies.
Supports installation and management of dependencies through npm, with commands for building and running the server.
Adaptive metacognitive oversight for autonomous AI agents – a research-backed MCP server keeping LLMs aligned, reflective and safe.
~10k+ downloads on PulseMCP and counting. Over 1k monthly tool calls via Smithery. Listed on 12+ orchestration platforms. Security rating 4.3 on MSEEP.ai.
VibeCheck MCP is a lightweight server implementing Anthropic's Model Context Protocol. It acts as an AI meta-mentor for your agents, interrupting pattern inertia with Critical Path Interrupts (CPI) to prevent Reasoning Lock-In (RLI). Think of it as a rubber-duck debugger for LLMs – a quick sanity check before your agent goes down the wrong path.
Large language models can confidently follow flawed plans. Without an external nudge they may spiral into overengineering or misalignment. VibeCheck provides that nudge through short reflective pauses, improving reliability and safety.
| Feature | Description | Benefits |
|---|---|---|
| CPI Adaptive Interrupts | Phase-aware prompts that challenge assumptions | alignment, robustness |
| Multi-provider LLM | Gemini, OpenAI and OpenRouter support | flexibility |
| History Continuity | Summarizes prior advice when sessionId is supplied | context retention |
| Optional vibe_learn | Log mistakes and fixes for future reflection | self-improvement |
vibe_learn loggingThis project targets Node 20+. If you see a TypeScript error about a duplicate require declaration when building with Node 20.19.3, ensure your dependencies are up to date (npm install) or use the Docker setup below which handles the build automatically.
Create a .env file with the API keys you plan to use:
Start the server:
See docs/TESTING.md for instructions on how to run tests.
The repository includes a helper script for one-command setup. It builds the image, saves your GEMINI_API_KEY and configures the container to start automatically whenever you log in:
This script:
~/vibe-check-mcp for persistent datadocker-compose.yml~/vibe-check-mcp/.envvibe-check-tcp-wrapper.sh which proxies Cursor IDE to the server
After running it, open Cursor IDE → Settings → MCP and add a new server of type Command pointing to:See Automatic Docker Setup for full details. If you prefer to run the commands manually:
Add to claude_desktop_config.json:
In your agent's system prompt, make it clear that vibe_check is a mandatory tool for reflection. Always pass the full user request and other relevant context. After correcting a mistake, you can optionally log it with vibe_learn to build a history for future analysis.
Example snippet:
| Tool | Purpose |
|---|---|
| 🛑 vibe_check | Challenge assumptions and prevent tunnel vision |
| 🔄 vibe_learn | Capture mistakes, preferences and successes |
See docs/philosophy.md for the alignment research behind VibeCheck. The approach draws inspiration from Reflexion, Constitutional AI and other high-trust frameworks.
This repository includes a CI-based security scan that runs on every pull request. It checks dependencies with npm audit and scans the source for risky patterns. See SECURITY.md for details and how to report issues.
Contributions are welcome! See CONTRIBUTING.md and join our Discord for discussion.
vibe_learn is optional.VibeCheck MCP is released under the MIT License. Built for reliable, enterprise-ready AI agents.
A metacognitive pattern interrupt system that helps prevent AI assistants from overcomplicated reasoning paths by providing external validation, simplification guidance, and learning mechanisms.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/PV-Bhat/vibe-check-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server