VERIFIED

Vibe Check

Safety: 65/100

0.0(0)

Vibe Check MCP is a research-backed AI meta-mentor that uses Chain-Pattern Interrupts (CPI) to keep agents aligned, reflective, and safe.

MCP ServersSearch & WebDevelopmentData & DatabasesProductivityAI & LLMUtilitiesFreemium

Boost this tool

Subscribe to listing upgrades or segmented pushes.

Overview

Vibe Check MCP is a research-backed AI meta-mentor that uses Chain-Pattern Interrupts (CPI) to keep agents aligned, reflective, and safe.

Vibe Check MCP enhances agent safety by providing metacognitive feedback and interrupting flawed reasoning. It is relatively safe when used with strong API key management and well-defined session constitutions. Risks increase if API keys are exposed or constitutions are misconfigured, potentially leading to unintended consequences or security breaches.

Performance depends on the LLM provider and the complexity of the session constitutions. CPI introduces latency due to the metacognitive feedback loop.

Cost is primarily driven by API calls to the LLM providers. Complex session constitutions and frequent CPI interventions can increase costs.

HybridTypeScript464 starsMITReleased 11/6/2025CI/CD

Connections & Capabilities

Connects To

GitHubDocker

Capabilities

ReadWriteExec

Client Compatibility

Claude Desktop

full

Cursor

full

Windsurf

full

VS Code (Copilot)

partial

Quickstart

Install

npx -y @pv-bhat/vibe-check-mcp start --stdio

Claude Desktop Config

{
  "mcpServers": {
    "vibe-check-mcp": {
      "command": "npx",
      "args": ["-y", "@pv-bhat/vibe-check-mcp", "start", "--stdio"]
    }
  }
}

Environment Variables

OPENAI_API_KEYANTHROPIC_API_KEYANTHROPIC_AUTH_TOKENANTHROPIC_BASE_URLMCP_TRANSPORTMCP_HTTP_PORT

Tools (3)

high

update_constitution

Merges or sets the rule set for a specific session.

Modifies session rules, potentially impacting agent behavior and access.

high

reset_constitution

Clears the session rules for a specific session.

Removes all session rules, potentially removing critical restrictions.

safe

check_constitution

Returns the effective rules for a specific session.

Read-only operation, no side effects.

Security

Auth Method

API Key

Data Locality

hybrid

Known Risks

!Exposure of API keys for LLM providers.
!Misconfiguration of session constitutions leading to unintended restrictions.
!Potential for reasoning lock-in if CPI is not effective.
!Dependency on external LLM providers introduces availability and security risks.
!HTTP transport vulnerabilities if not properly secured.

Safety Score

moderate risk

Positive

+Uses a second LLM for metacognitive feedback, adding a layer of oversight.
+Implements Chain-Pattern Interrupts (CPI) to prevent reasoning lock-in.
+Supports session constitutions to enforce rules per session.
+Offers optional vibe_learn for self-improvement through logging mistakes and fixes.
+Provides history continuity by summarizing prior advice when a sessionId is supplied.

Risks

-Relies on external LLM providers (Gemini, OpenAI, Anthropic, OpenRouter) which introduces dependency risks.
-Requires API keys for LLM providers, potentially exposing secrets if not managed correctly.
-Session constitutions, if not properly configured, could lead to unintended restrictions or bypasses.
-HTTP transport exposes an endpoint that needs proper security measures to prevent unauthorized access.
-Write operations are possible via constitution updates, posing a risk if exploited.

Use Cases

Agent Alignment

-Ensuring agents adhere to predefined guidelines.
-Preventing agents from generating harmful or inappropriate content.
-Maintaining consistent agent behavior across different sessions.

Reasoning Improvement

-Interrupting flawed reasoning patterns.
-Encouraging agents to reflect on their actions.
-Improving the reliability of agent outputs.

Security Enhancement

-Restricting agent access to sensitive resources.
-Preventing agents from performing unauthorized actions.
-Enforcing security policies within agent sessions.

Context Management

-Maintaining session history
-Adapting to changing session requirements
-Ensuring continuity of agent behavior

Who Is This For?

Best For

Developers building AI agents that require alignment and safety.
Organizations seeking to improve the reliability of AI agent outputs.
Teams implementing AI agents in sensitive or regulated environments.
Researchers exploring metacognitive feedback in AI systems.
Users needing a rubber-duck debugger for LLMs

Not Ideal For

Simple AI agents that do not require complex reasoning or alignment.
Resource-constrained environments where the overhead of CPI is prohibitive.
Scenarios where real-time performance is critical and latency is unacceptable.
Use cases where API key management is not feasible or secure.

Autonomy & Execution

Default ModeConfigurable

Autonomy is configurable via session constitutions, allowing for fine-grained control over agent behavior and access to resources.

StatelessNo

Retry LogicNot documented

ConcurrencySingle-threaded

Production Tip

Implement robust API key management and regularly review session constitutions to ensure optimal security and alignment.

FAQ

What is Chain-Pattern Interrupt (CPI)?

CPI is a technique used to interrupt flawed reasoning patterns in LLMs by introducing reflective pauses and metacognitive feedback.

How does Vibe Check MCP improve agent safety?

Vibe Check MCP improves agent safety by providing metacognitive feedback, enforcing session constitutions, and preventing reasoning lock-in.

What LLM providers are supported?

Vibe Check MCP supports Gemini, OpenAI, Anthropic, and OpenRouter.

How are API keys managed?

API keys are managed through environment variables or configuration files. Secure storage and access control are essential.

What are session constitutions?

Session constitutions are rules that define the behavior and access rights of an agent within a specific session.

How do I install Vibe Check MCP?

You can install Vibe Check MCP using npx or by cloning the repository and using npm.

What is the default transport?

The default transport is stdio, but HTTP is also supported.

Key Features

Search & Web Development Data & Databases Productivity AI & LLM Utilities

Metrics

Discovered2/14/2026

Reviews0

Saved By0 users

Related Tools

Vibe Check | AI Builder Hub Review & Alternatives | Flaex AI