A
licenseA
qualityB
maintenanceA Model Context Protocol server that empowers AI agents with metacognitive monitoring to detect reasoning loops and provide intelligent recovery using case-based reasoning and statistical analysis.
9
12 npm
9
MIT
Vibe Check MCP
by PV-Bhat
🧠 바이브 체크 MCP
또한 mcpservers.org , Glama.ai , mcp.so 에서 Vibecheck를 찾아보세요.
AI가 스스로 고무 오리를 만들 수 없을 때, 그 AI의 내부에 있는 고무 오리가 작동합니다.
바이브 체크란 무엇인가요?
"바이브 코딩" 시대에 AI 에이전트는 이제 놀라운 능력을 갖추게 되었지만, 이제 질문은 다음과 같이 바뀌었습니다.
~에서
"우리 AI 에이전트가 정말 이렇게 복잡한 작업을 수행할 수 있을까?"
에게
"제가 수십억 달러 규모의 기술 회사를 위한 인프라가 아닌 간단한 프로그램을 작성하고 싶어한다는 것을 AI 에이전트가 이해할 수 있을까요?"
AI 에이전트가 현재 제공하지 않는 필수적인 "잠깐만... 이게 아니야" 순간을 제공합니다. 바로 자체 수정 감독 계층입니다. Vibe Coder의 완벽한 정신 건강 점검 MCP 서버입니다.
전략적 패턴 인터럽트를 구현하여 AI 워크플로에서 연쇄 오류가 발생하는 것을 방지합니다.
LearnLM 1.5 Pro(Gemini API)와 함께 "Vibe Check"라는 도구를 사용하여 교육학 및 메타인지에 맞게 미세 조정하여 복잡한 워크플로 전략을 강화하고 터널 비전 오류를 방지합니다.
"Vibe Distill"을 구현하여 계획 단순화를 장려하고, 과도한 솔루션 엔지니어링을 방지하고, 상담원의 상황적 편차를 최소화합니다.
자체 개선 피드백 루프: 에이전트는 "Vibe Learn"에 실수를 기록하여 의미적 회수를 개선하고 감독 AI가 시간 경과에 따라 패턴을 타겟팅하도록 도울 수 있습니다.
요약: 에이전트를 중지하고 잘못된 작업을 수행하기 전에 다시 고려하도록 미세 조정된 에이전트를 구현합니다.
Related MCP server: Visum Thinker MCP Server
문제: 패턴 관성
바이브 코딩 운동에서 우리는 모두 LLM을 사용하여 코드를 생성하고, 리팩토링하고, 디버깅합니다. 하지만 이러한 모델에는 치명적인 결함이 있습니다. 일단 추론 경로로 접어들면, 그 경로가 명백히 잘못되었음에도 불구하고 계속 추론 경로를 따라간다는 것입니다.
지엑스피1
이 패턴 관성은 다음과 같은 결과를 초래합니다.
🔄 터널 비전 : 에이전트가 한 가지 접근 방식에 갇혀 대안을 찾지 못하는 경우
📈 범위 확장 : 간단한 작업이 점차 기업 규모 솔루션으로 발전합니다.
🔌 과도한 엔지니어링 : 필요하지 않은 문제에 추상화 계층을 추가하는 것
❓ 정렬 불량 : 요청한 문제와 인접해 있지만 다른 문제를 해결함
특징: 메타인지 감독 도구
Vibe Check는 세 가지 통합 도구를 통해 에이전트 워크플로에 메타인지 계층을 추가합니다.
🛑 바이브 체크
터널 비전을 깨는 메타인지적 질문으로 패턴 인터럽트 메커니즘을 구현합니다.
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
복잡한 워크플로를 재조정하는 메타 사고 앵커 포인트 :
vibe_distill({
"plan": "...", // Detailed plan to simplify
"userRequest": "..." // FULL original user request
})🔄 바이브런
시간이 지남에 따라 패턴 인식을 구축하는 자체 개선 피드백 루프 :
vibe_learn({
"mistake": "...", // One-sentence description of mistake
"category": "...", // From standard categories
"solution": "..." // How it was corrected
})Vibe Check 실행
진동 체크 전:
Claude는 모호함에도 불구하고 MCP의 의미를 가정하여 이후의 모든 단계에서 이 잘못된 가정을 하게 됩니다.
진동 확인 후:
Vibe Check MCP가 호출되어 모호성을 지적하고 Claude가 정보 부족을 인정하고 이를 적극적으로 해결하도록 강요합니다.
설치 및 설정
Smithery를 통해 설치
Smithery를 통해 Claude Desktop에 vibe-check-mcp-server를 자동으로 설치하려면:
npx -y @smithery/cli install @PV-Bhat/vibe-check-mcp-server --client claudenpm을 통한 수동 설치(권장)
# 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 startClaude와의 통합
claude_desktop_config.json 에 다음을 추가하세요:
"vibe-check": {
"command": "node",
"args": [
"/path/to/vibe-check-mcp/build/index.js"
],
"env": {
"GEMINI_API_KEY": "YOUR_GEMINI_API_KEY"
}
}환경 구성
프로젝트 루트에 .env 파일을 만듭니다.
GEMINI_API_KEY=your_gemini_api_key_here에이전트 프롬프트 가이드
효과적인 패턴 인터럽트를 위해 시스템 프롬프트에 다음 지침을 포함하세요.
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 issues각 도구를 사용하는 시기
도구 | 언제 사용할 것인가 |
🛑 바이브 체크 | 에이전트가 Todo 앱에 대한 블록체인 기본 사항을 설명하기 시작할 때 |
⚓ vibe_distill | 에이전트의 계획에 전체 기술 사양보다 중첩된 요점이 더 많은 경우 |
🔄 바이브런 | 복잡성의 심연에서 에이전트를 수동으로 조종한 후 |
API 참조
전체 API 문서는 기술 참조 에서 확인하세요.
건축학
Vibe Check는 재귀적 감독 원칙을 기반으로 이중 계층 메타인지 아키텍처를 구현합니다. 주요 통찰력:
패턴 관성 저항 : LLM 에이전트는 추론 경로에서 자연스럽게 모멘텀과 유사한 속성을 보이므로 방향을 바꾸기 위해 외부 개입이 필요합니다.
위상 공명 방해 : 메타인지적 질문은 최대의 교정 효과를 얻기 위해 에이전트의 현재 단계(계획/구현/검토)와 일치해야 합니다.
권한 구조 통합 : 에이전트는 외부 메타인지 피드백을 선택적인 제안이 아닌 최우선순위 방해로 처리하도록 명시적으로 촉구받아야 합니다.
앵커 압축 메커니즘 : 복잡한 추론 흐름은 효과적인 재조정 지점 역할을 하기 위해 최소한의 앵커 체인으로 정제되어야 합니다.
재귀적 피드백 루프 : 관찰된 모든 실수는 저장되어야 하며, 이를 활용하여 인터럽트 효율성을 개선하는 종단적 실패 모델을 구축해야 합니다.
기본 설계 원칙에 대한 자세한 내용은 철학을 참조하세요.
Vibe Check 실행 (계속)
선적 서류 비치
문서 | 설명 |
에이전트 통합을 위한 세부 기술 | |
피드백 체이닝, 신뢰 수준 등 | |
완전한 API 문서 | |
Vibe Check의 더 심층적인 AI 정렬 원리 | |
Vibe Check의 실제 사례 |
기여하다
Vibe Check에 기여해 주세요! 버그 수정, 기능 추가, 문서 개선 등 어떤 참여든 시작하려면 기여 가이드라인을 확인하세요.
특허
Available Tools
2 toolsvibe_checkB
Metacognitive questioning tool that identifies assumptions and breaks tunnel vision to prevent cascading errors
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| goal | Yes | The agent's current goal | |
| modelOverride | No | ||
| plan | Yes | The agent's detailed plan | |
| progress | No | The agent's progress so far | |
| sessionId | No | Optional session ID for state management | |
| taskContext | No | The context of the current task | |
| uncertainties | No | The agent's uncertainties | |
| userPrompt | No | The original user prompt |
TDQS
B3.2/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the tool's cognitive effects (identifying assumptions, breaking tunnel vision, preventing errors) but lacks details on how it operates (e.g., does it generate questions, provide feedback, modify plans?), what it returns, or any constraints like rate limits or permissions. This leaves significant gaps in understanding its behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the key purpose ('metacognitive questioning tool') and elaborates with clear outcomes. Every word earns its place, avoiding redundancy or fluff, making it highly concise and well-structured for quick understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (8 parameters, no annotations, no output schema), the description is incomplete. It doesn't explain what the tool returns, how it uses the parameters (e.g., 'modelOverride' for AI model selection), or behavioral details like state management with 'sessionId.' For a metacognitive tool with rich inputs, more context is needed to guide effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is high (88%), so the schema already documents most parameters well (e.g., 'goal,' 'plan,' 'uncertainties'). The description doesn't add specific meaning beyond the schema, such as explaining how parameters like 'modelOverride' or 'sessionId' relate to the tool's purpose. Baseline 3 is appropriate as the schema does the heavy lifting, but no extra value is provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as a 'metacognitive questioning tool' that 'identifies assumptions and breaks tunnel vision to prevent cascading errors.' It uses specific verbs ('identifies,' 'breaks,' 'prevent') and describes the cognitive function, though it doesn't explicitly differentiate from its sibling 'vibe_learn' beyond the general domain of 'vibe' tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage in scenarios involving assumptions, tunnel vision, or error prevention, suggesting it's for reflective or corrective moments. However, it doesn't provide explicit guidance on when to use this tool versus 'vibe_learn' or other alternatives, nor does it specify prerequisites or exclusions, leaving the context somewhat open-ended.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
vibe_learnC
Pattern recognition system that tracks common errors and solutions to prevent recurring issues
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| category | Yes | Category (standard categories: Complex Solution Bias, Feature Creep, Premature Implementation, Misalignment, Overtooling, Preference, Success, Other) | |
| mistake | Yes | One-sentence description of the learning entry | |
| sessionId | No | Optional session ID for state management | |
| solution | No | How it was corrected (if applicable) | |
| type | No | Type of learning entry |
TDQS
C2.9/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions tracking and prevention but fails to detail critical aspects like whether this is a read/write operation, data persistence, permissions needed, or error handling. This leaves significant gaps for a tool with 5 parameters and potential data mutation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without redundancy or unnecessary details. It is front-loaded and appropriately sized for its informational content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (5 parameters, no annotations, no output schema), the description is incomplete. It lacks details on behavioral traits, output expectations, and differentiation from siblings, making it inadequate for guiding an agent in practical use beyond a high-level purpose.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, providing clear documentation for all 5 parameters. The description adds no additional parameter semantics beyond what's in the schema, so it meets the baseline of 3 without compensating or enhancing the schema's information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as a 'pattern recognition system that tracks common errors and solutions to prevent recurring issues,' which specifies the verb (tracks) and resource (errors/solutions). However, it doesn't explicitly differentiate from its sibling 'vibe_check,' leaving room for ambiguity about their distinct roles.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, including its sibling 'vibe_check.' It lacks context about prerequisites, timing, or exclusions, leaving the agent to infer usage based on the purpose alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
v1.0.0- First observed
vibe_check - First observed
vibe_learn
TDQS
B3.3/5.0
Scored across 2 tools
Disambiguation5/5
The two tools have clearly distinct purposes: vibe_check focuses on metacognitive questioning to prevent immediate errors by identifying assumptions, while vibe_learn focuses on pattern recognition to prevent recurring issues by tracking errors and solutions. There is no overlap or ambiguity between them.
Naming Consistency5/5
Both tools follow a consistent 'vibe_' prefix pattern with descriptive suffixes (check and learn), making them predictable and readable. The naming style is uniform throughout the set.
Tool Count3/5
With only 2 tools, the set feels thin for a server named 'Vibe Check MCP', which suggests a broader scope for metacognitive or error-prevention functionality. While the tools are well-defined, the count is borderline low for typical MCP server purposes.
Completeness3/5
The tools cover two key aspects of error prevention (immediate and recurring), but there are notable gaps such as tools for applying learned patterns, adjusting strategies based on feedback, or integrating with external systems. The surface is functional but not fully comprehensive for the inferred domain.
Maintenance
ActivitySlowing
ResponsivenessSlow
Related MCP Connectors
Adversarial behavioural-bias engine — audits your decisions for cognitive biases via your own AI.
Patterns for designing and reviewing AI skills, agents, and multi-agent workflows. Find guidance on context economy, delegation, verification, and tool design; inspect claims, worked examples, maturity labels, and source references. Five read-only tools let agents discover relevant patterns, compare concise cards, read specific sections, and explore relationships. Hosted Streamable HTTP at https://agentic-atlas.dev/mcp/ — no installation, account, or API key required. Browse the atlas at https://agentic-atlas.dev/.
Goal and task planning MCP for Codex and AI agents, with evidence-backed completion.
A governed, nonclinical reasoning system that helps people and AI agents make sense of difficult moments and choose a grounded next step. Use Clarity OS for overthinking, emotional activation, uncertainty, decision friction, conflicting priorities, repeating patterns, or difficult conversations. It returns structured, safety-governed clarity while preserving uncertainty, personal agency, and appropriate nonclinical boundaries.
Related MCP Servers
- AlicenseBqualityNot gradedmaintenanceProvides structured sequential thinking capabilities for AI assistants to break down complex problems into manageable steps, revise thoughts, and explore alternative reasoning paths.29-
- AlicenseNot gradedqualityDmaintenanceProvides structured thinking tools including mental models, design patterns, debugging approaches, decision frameworks, and multi-persona reasoning to enhance AI assistant problem-solving capabilities.7 npmMIT
- AlicenseNot gradedqualityDmaintenanceProvides a 'reflect' tool that creates cognitive checkpoints for AI assistants, forcing structured step-by-step reasoning through complex problems to improve accuracy and maintain context during task execution.4 npm6MIT