Supports deployment on Cloudflare Workers platform for running the vibe check oversight server
Provides containerized deployment with automated setup scripts for running the metacognitive oversight server
Supports OpenAI as an LLM provider for powering the metacognitive oversight and reflection capabilities
References research published on ResearchGate that validates the Chain-Pattern Interrupt methodology used by the server
Provides archival DOI links to research materials validating the CPI oversight methodology
π§ Vibe Check MCP v2.5.1
Plug-and-play metacognitive oversight layer for autonomous AI agents β a research-backed MCP server keeping LLMs aligned, reflective and safe.
Recognition
Listed in Anthropicβs official Model Context Protocol repo π
Discoverable in the official MCP Registry π
18k+ installs across public MCP directories/clients
Table of Contents
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 β 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
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 βconstitutionβ to enforce rules per sessionId
that CPI will honor. Typical uses: βno external network calls,β βprefer unit tests before refactors,β βnever write secrets to disk.β
API (tools):
update_constitution({ sessionId, rules })
β merges/sets rule set for the sessionreset_constitution({ sessionId })
β clears session rulescheck_constitution({ sessionId })
β 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
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:
Start the server:
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:
This script:
Creates
~/vibe-check-mcp
for persistent dataBuilds 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 β Settings β 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:
Integrating with Claude Desktop
Add to claude_desktop_config.json
:
Research & Philosophy
CPI (Chain-Pattern Interrupt) is the research-backed oversight method behind Vibe Check. It injects brief, well-timed βpause pointsβ at risk inflection moments to re-align the agent to the userβs true priority, preventing destructive cascades and reasoning lock-in (RLI). In pooled evaluation across 153 runs, CPI nearly doubles success (~27%β54%) and roughly halves harmful actions (~83%β42%). Optimal interrupt dosage is ~10β20% of steps. Vibe Check MCP implements CPI as an external mentor layer at test time.
Links:
π CPI Paper (ResearchGate) β http://dx.doi.org/10.13140/RG.2.2.18237.93922
π CPI Reference Implementation (GitHub): https://github.com/PV-Bhat/cpi
π MURST Zenodo DOI (RSRC archival): https://doi.org/10.5281/zenodo.14851363
Usage Examples
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:
When to Use Each Tool
Tool | Purpose |
π vibe_check | Challenge assumptions and prevent tunnel vision |
π vibe_learn | Capture mistakes, preferences, and successes |
π§° update_constitution | Set/merge session rules the CPI layer will enforce |
π§Ή reset_constitution | Clear rules for a session |
π 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
π MSEEP
π‘ MCP Servers
π§ MCP.so
π οΈ Creati.ai
π‘ Pulse MCP
π Playbooks.com
π§° MCPHub.tools
π MCP Directory
π§ MagicSlides
ποΈ AIAgentsList
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
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
Custom version of vibecheck
- Recognition
- Table of Contents
- What is Vibe Check MCP?
- Overview
- Architecture
- The Problem: Pattern Inertia & Reasoning Lock-In
- Key Features
- What's New in v2.5.1
- Session Constitution (per-session rules)
- Quickstart & Installation
- Research & Philosophy
- Usage Examples
- Adaptive Metacognitive Interrupts (CPI)
- Agent Prompting Essentials
- When to Use Each Tool
- Documentation
- Security
- Roadmap
- Contributing & Community
- FAQ
- Find Vibe Check MCP on
- Star History
- Credits & License
- Author Credits & Links