Cursorのための決定論的アーキテクチャエンジンおよび論理デッドロックプロトコル
プロジェクトの複雑さが増すと、AIプログラミングはしばしば「ハルシネーションの螺旋」に陥ります。VibeLogic MCPは単なるコード生成ツールではなく、「人間の意図」と「コード実行」の間に位置する管理レイヤーです。AIがコードを変更する前に、視覚的な設計図を通じて監査を行うことを強制します。
視覚的アーキテクチャ監査 (Visual Audit)：AIにプロジェクトのトポロジーを抽出させ、Mermaid設計図を通じてロジックを整合させることで、意図の100%の決定論を保証します。
論理デッドロックプロトコル (Security Lock)：独自にカプセル化されたアテンション・ハイジャック・プロトコルにより、「図面の確認」が行われるまでAIを待機させ、権限外のリファクタリングを阻止します。
ファイル横断的な詳細追跡：複数ファイルの関連変更を自動的に識別し、構造化された施工リスト (Action Plan) を生成します。
資産化アーカイブ：すべてのアーキテクチャ決定を自動的に .md ファイルとしてエクスポートし、プロジェクトのアーキテクチャ進化ログとして永続的に蓄積します。
Related MCP server: mcp-edit-math
Node.jsがインストールされていることを確認し、Cursorで直接実行してください：
npx vibelogic-mcpCursorの Settings -> Features -> MCP を開きます。 「+ Add New MCP Server」をクリックします。 以下のように設定してください：
{
"mcpServers": {
"VibeLogic": {
"command": "npx.cmd",
"args": [
"-y",
"vibelogic-mcp@latest"
]
}
}
}"この機能のロジックを分析して。図が見たい。" "ログインモジュールの検証フローをリファクタリングしたい。先に図面と施工リストを出して。" "現在のコードに基づいて、新しいAPIが既存のアーキテクチャに与える影響を監査して。"
BYOK (Bring Your Own Key)：VibeLogicはローカル環境で動作し、コードを一切保存しません。Cursorで選択したモデルの能力を完全に再利用します。 複雑化の拒否：コアロジックの変更に関わる場合にのみアクティブ化され、通常のUI調整やバグ修正には干渉しません。
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.
