🧠 Vibe Check MCP v2.5.1

Plug-and-play metacognitive oversight layer for autonomous AI agents – a research-backed MCP server keeping LLMs aligned, reflective and safe.

Recognition

Listed in Anthropic’s official Model Context Protocol repo 🔗
Discoverable in the official MCP Registry 🔗
18k+ installs across public MCP directories/clients

Version Trust Score smithery badge Security 4.3★ on MSEEP PRs Welcome

What is Vibe Check MCP?

Vibe Check 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 Chain-Pattern 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.

Overview

Vibe Check MCP pairs a metacognitive signal layer with CPI so agents can pause when risk spikes. Vibe Check surfaces traits, uncertainty, and risk scores; CPI consumes those triggers and enforces an intervention policy before the agent resumes. See the CPI integration guide and the CPI repo at https://github.com/PV-Bhat/cpi for wiring details.

Architecture

Vibe Check runs alongside your agent workflow, emitting signals that downstream overseers like CPI or human reviewers can act on. The high-level component map lives in docs/architecture.md, while the CPI handoff diagram and example shim are captured in docs/integrations/cpi.md.

The Problem: Pattern Inertia & Reasoning Lock-In

Large language models can confidently follow flawed plans. Without an external nudge they may spiral into overengineering or misalignment. Vibe Check provides that nudge through short reflective pauses, improving reliability and safety.

Key Features

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

What's New in v2.5.1

Session Constitution (per-session rules)

Use a lightweight “constitution” to enforce rules per sessionId that CPI will honor. Typical uses: “no external network calls,” “prefer unit tests before refactors,” “never write secrets to disk.”

API (tools):

update_constitution({ sessionId, rules }) → merges/sets rule set for the session
reset_constitution({ sessionId }) → clears session rules
check_constitution({ sessionId }) → returns effective rules for the session as a JSON string in text format for broad MCP client compatibility

Response Format Note: The check_constitution tool returns its data with type: 'text' containing a JSON string (rather than type: 'json') to ensure compatibility with the widest range of MCP clients. Clients will need to parse the text field to access the JSON data.

Quickstart & Installation

# Clone and install git clone https://github.com/PV-Bhat/vibe-check-mcp-server.git cd vibe-check-mcp-server npm install npm run build

This 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:

# Gemini (default) GEMINI_API_KEY=your_gemini_api_key # Optional providers OPENAI_API_KEY=your_openai_api_key OPENROUTER_API_KEY=your_openrouter_api_key # Optional overrides DEFAULT_LLM_PROVIDER=gemini DEFAULT_MODEL=gemini-2.5-pro

Start the server:

npm start

See docs/TESTING.md for instructions on how to run tests.

Docker

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:

bash scripts/docker-setup.sh

This script:

Creates ~/vibe-check-mcp for persistent data
Builds the Docker image and sets up docker-compose.yml
Prompts for your API key and writes ~/vibe-check-mcp/.env
Installs a systemd service (Linux) or LaunchAgent (macOS) so the container starts at login
Generates vibe-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:

~/vibe-check-mcp/vibe-check-tcp-wrapper.sh

See Automatic Docker Setup for full details. If you prefer to run the commands manually:

docker build -t vibe-check-mcp . docker run -e GEMINI_API_KEY=your_gemini_api_key -p 3000:3000 vibe-check-mcp

Integrating with Claude Desktop

Add to 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" } }

Research & Philosophy

CPI (Chain-Pattern Interrupt) is the research-backed oversight method behind Vibe Check. It injects brief, well-timed “pause points” at risk inflection moments to re-align the agent to the user’s true priority, preventing destructive cascades and reasoning lock-in (RLI). In pooled evaluation across 153 runs, CPI nearly doubles success (~27%→54%) and roughly halves harmful actions (~83%→42%). Optimal interrupt dosage is ~10–20% of steps. Vibe Check MCP implements CPI as an external mentor layer at test time.

Links:

📄 CPI Paper (ResearchGate) — http://dx.doi.org/10.13140/RG.2.2.18237.93922
📘 CPI Reference Implementation (GitHub): https://github.com/PV-Bhat/cpi
📚 MURST Zenodo DOI (RSRC archival): https://doi.org/10.5281/zenodo.14851363

Usage Examples

import { vibe_check } from 'vibe-check-mcp'; const result = await vibe_check({ goal: 'Write unit tests', plan: 'Use vitest for coverage', sessionId: 'demo1' }); console.log(result.questions);

flowchart TD A[Agent Phase] --> B{Monitor Progress} B -- high risk --> C[CPI Interrupt] C --> D[Reflect & Adjust] B -- smooth --> E[Continue]

Adaptive Metacognitive Interrupts (CPI)

Agent Prompting Essentials

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:

As an autonomous agent you will: 1. Call vibe_check after planning and before major actions. 2. Provide the full user request and your current plan. 3. Optionally, record resolved issues with vibe_learn.

When to Use Each Tool

Tool	Purpose
🛑 vibe_check	Challenge assumptions and prevent tunnel vision
🔄 vibe_learn	Capture mistakes, preferences, and successes
🧰 update_constitution	Set/merge session rules the CPI layer will enforce
🧹 reset_constitution	Clear rules for a session
🔎 check_constitution	Inspect effective rules for a session (returns JSON as text for MCP compatibility)

Documentation

Security

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.

Roadmap

Benchmarks and latency profiling
Adaptive tuning based on agent performance
Multi-agent cooperation support
Optional human-in-the-loop review

Contributing & Community

Contributions are welcome! See CONTRIBUTING.md.

FAQ

Does it increase latency? A single CPI call typically adds ~1 second depending on the provider.
Can I disable logging? Yes, vibe_learn is optional.

Find Vibe Check MCP on

Star History

Credits & License

Vibe Check MCP is released under the MIT License. Built for reliable, enterprise-ready AI agents.

Author Credits & Links

Vibe Check MCP created by: Pruthvi Bhat, Intiative - https://murst.org/

This server cannot be installed

-

security - not tested

A

license - permissive license

-

quality - not tested

How are these scores calculated?

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

Custom version of vibecheck

mcp-vibe-check