Motor de arquitectura determinista y protocolo de bloqueo lógico para Cursor
Cuando la complejidad de un proyecto aumenta, la programación con IA a menudo cae en una "espiral de alucinaciones". VibeLogic MCP no es otro generador de código, sino una capa de control situada entre la "intención humana" y la "ejecución del código". Obliga a la IA a realizar una auditoría mediante planos visuales antes de realizar cualquier modificación en el código.
Auditoría de arquitectura visual (Visual Audit): Obliga a la IA a extraer la topología del proyecto y alinear la lógica mediante planos de Mermaid, garantizando una determinación de intención del 100%.
Protocolo de bloqueo lógico (Security Lock): Protocolo exclusivo de secuestro de atención que obliga a la IA a permanecer en espera hasta que se confirme el "plano", bloqueando refactorizaciones no autorizadas.
Seguimiento profundo entre archivos: Identifica automáticamente cambios relacionados en múltiples archivos y genera una lista de tareas estructurada (Action Plan).
Archivo de activos: Todas las decisiones arquitectónicas se exportan automáticamente como archivos .md, consolidándose permanentemente como el registro de evolución arquitectónica del proyecto.
Related MCP server: mcp-edit-math
Asegúrate de tener instalado Node.js y luego ejecuta directamente en Cursor:
npx vibelogic-mcpAbre Cursor Settings -> Features -> MCP. Haz clic en + Add New MCP Server. Configúralo de la siguiente manera:
{
"mcpServers": {
"VibeLogic": {
"command": "npx.cmd",
"args": [
"-y",
"vibelogic-mcp@latest"
]
}
}
}"Ayúdame a analizar la lógica de esta funcionalidad, quiero ver el diagrama." "Quiero refactorizar el flujo de validación del módulo de inicio de sesión, primero genera el diagrama y la lista de tareas." "Basado en el código actual, audita el impacto de la nueva API en la arquitectura existente."
BYOK (Trae tu propia clave): VibeLogic se ejecuta en tu entorno local, no almacena ningún código y reutiliza completamente las capacidades del modelo seleccionado en tu Cursor. Sin complicaciones: Se activa solo cuando hay cambios en la lógica central, sin interferir con ajustes de UI rutinarios o corrección de errores.
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.
