Cursor를 위한 결정론적 아키텍처 엔진 및 논리적 데드락 프로토콜
프로젝트 복잡도가 증가하면 AI 프로그래밍은 종종 '환각의 소용돌이'에 빠지게 됩니다. VibeLogic MCP는 단순한 코드 생성기가 아니라 '인간의 의도'와 '코드 실행' 사이에 위치한 제어 계층입니다. 이 엔진은 AI가 코드를 수정하기 전에 시각적 청사진을 통해 감사를 수행하도록 강제합니다.
시각적 아키텍처 감사 (Visual Audit): AI가 프로젝트 토폴로지를 추출하도록 강제하고, Mermaid 청사진을 통해 논리를 정렬하여 100% 의도 결정론을 보장합니다.
논리적 데드락 프로토콜 (Security Lock): 독점적으로 캡슐화된 주의력 하이재킹 프로토콜을 통해 AI가 '도면 확인' 전까지 대기 상태를 유지하도록 하여 무단 리팩토링을 차단합니다.
파일 간 심층 추적: 다중 파일 연관 변경 사항을 자동으로 식별하고 구조화된 작업 목록(Action Plan)을 생성합니다.
자산화 아카이브: 모든 아키텍처 결정 사항은 자동으로 .md 파일로 내보내지며, 프로젝트의 아키텍처 진화 로그로 영구 보존됩니다.
Related MCP server: mcp-edit-math
Node.js가 설치되어 있는지 확인한 후, Cursor에서 직접 실행하세요:
npx vibelogic-mcpCursor Settings -> Features -> MCP를 엽니다.
Add New MCP Server를 클릭합니다. 다음과 같이 설정하세요:
{
"mcpServers": {
"VibeLogic": {
"command": "npx.cmd",
"args": [
"-y",
"vibelogic-mcp@latest"
]
}
}
}"이 기능의 논리를 분석해 줘, 다이어그램으로 보고 싶어." "로그인 모듈의 검증 프로세스를 리팩토링할 거야, 먼저 도면과 작업 목록을 만들어 줘." "현재 코드를 기반으로 새로운 API가 기존 아키텍처에 미치는 영향을 감사해 줘."
BYOK (Bring Your Own Key): VibeLogic은 로컬 환경에서 실행되며 코드를 저장하지 않고, Cursor에서 선택한 모델 기능을 그대로 활용합니다. 복잡성 거부: 핵심 논리 변경이 포함된 경우에만 활성화되며, 일반적인 UI 조정이나 버그 수정에는 간섭하지 않습니다.
仅在涉及项目核心逻辑变更、新增功能、跨文件流程修改，或用户明确要求“查看项目逻辑”、“查看当前项目实现”时调用。 警告：对于调整简单参数、常数、阈值、纯 UI 颜色/样式微调、补充注释、变量重命名、局部语法 Bug 修复等不涉及核心逻辑变动的操作，严禁调用此工具。
| Name | Required | Description | Default |
|---|---|---|---|
| intent | Yes | 用户意图：'view' 表示仅查看，'modify' 表示重构。 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It does not describe what the tool does (e.g., whether it reads or modifies, side effects, return values). It only states when to call, missing essential behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is concise and front-loaded with usage conditions. While slightly verbose with the warning, it remains efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should explain return values or effect of the tool. It only covers when to call, leaving the agent without knowledge of what to expect from invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a single parameter 'intent' that has an enum and description. The description adds no additional meaning beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool is for core logic changes, new features, cross-file modifications, or when user asks to view project logic. It distinguishes what is not its purpose (trivial changes) effectively, despite having no sibling tools to differentiate from.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly specifies when to call and when not to call, with concrete examples of allowed and forbidden use cases. This provides strong guidance for an AI agent to select the appropriate tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0get_logic_blueprintScored across 1 tool
With only one tool, there is no risk of confusion between tools.
The single tool uses a verb_noun pattern (get_logic_blueprint), and with only one tool, consistency is not an issue.
One tool is too few for a server named 'vibelogic', which suggests a need for multiple logic-related operations. The tool is also highly restricted in usage, further limiting its utility.
A single tool cannot cover the expected lifecycle or operations for logic manipulation. The tool itself warns against many common tasks, leaving obvious gaps.
Deterministic AI code review, with an audit record. Governance inside the agent loop.
Let Claude, Cursor, or ChatGPT author Mermaid diagrams your team can read and share.
AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
