convez.ai
MCP ServerDados & AnalyticsAvançado
agrhub

VibeMongo Admin — Dashboard IA para MongoDB

agrhub/vibe-mongo-admin

Admin MongoDB com SRE autônomo e Gemini integrado

Ver no GitHub
InicialPluginScore · de 0 a 100

Dashboard moderno de administração MongoDB com IA integrada, construído sobre Vue 3, Express, Google ADK e MCP Server. Oferece monitoramento autônomo de performance, otimização de índices com IA, chat contextual para consultas em linguagem natural e observabilidade em tempo real via Arize Phoenix.

Instalação

$npx convez-ai agrhub/vibe-mongo-admin

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
37%
Último commit
há 5 meses
Versão
—
Issues abertas
2
Contribuidores
4

Casos de uso

  • Otimizar queries MongoDB com sugestões de IA baseadas em traces
  • Monitorar performance de banco em tempo real e identificar slow queries
  • Escrever agregações MongoDB em linguagem natural via chat
  • Analisar e debugar operações de banco com IA judge evaluation

Veredito

Ferramental ambicioso que reimagina admin de MongoDB com IA e observabilidade. Excelente para times que precisam otimização autônoma de queries e monitoramento SRE, mas requer infraestrutura Google Cloud e conhecimento técnico substancial.

README

A tradução para o português deste README ainda está na fila.

VibeMongo Admin — Documentation

VibeMongo Admin

A modern, AI-first MongoDB administration dashboard powered by a triad of cutting-edge technologies: Google Cloud Agent (ADK & Gemini), the MongoDB MCP Server, and Arize Phoenix Cloud & MCP for autonomous monitoring and LLM evaluation.


📚 Table of Contents

DocumentDescription
Premium AI SRE Upgrades[NEW] Deep-dive into Schema Migrator, ERD, Webhooks, Index Sanitizer, and Mock Gen
Architecture OverviewSystem design, component diagram, and data flow
Client GuideVue 3 frontend — setup, structure, and configuration
Backend GuideExpress API + Google ADK Agent — setup, structure, and configuration
AI Agent GuideGoogle ADK + MongoDB MCP Server integration deep-dive
Deploy — Cloud RunStep-by-step deploy to Google Cloud Run
Deploy — Cloud AgentDeploy the AI Agent as a Google Cloud Agent Engine service
Workflow DiagramsDetailed sequence diagrams: VibeMongo ↔ ADK ↔ MCP ↔ MongoDB

Inspiration

Managing MongoDB databases using traditional GUI clients often involves writing complex, syntax-heavy aggregation pipelines just to get simple answers. For developers who are not MongoDB experts, writing these pipelines can be a huge time sink. Furthermore, monitoring database performance and identifying slow queries usually requires jumping into completely separate APM (Application Performance Monitoring) tools.

We were inspired to build a modern, web-based admin interface that combines the robust features of traditional database clients with the power of generative AI and real-time observability. Our goal was to create a "Vibe" where managing databases feels effortless, intuitive, and conversational, while also introducing Autonomous Database SRE capabilities.

🚀 Why VibeMongo? (The Autonomous DB SRE)

While traditional tools like MongoDB Compass offer solid administration, VibeMongo rethinks the database management experience by integrating generative AI and real-time observability deeply into the workflow:

  1. DB-Guardian Copilot (AI-Driven SRE)
    • VibeMongo actively monitors query performance in real-time.
    • Using the Arize Phoenix MCP, it captures trace data and flags slow queries. The built-in AI agent (Google ADK) can then analyze the trace waterfall and suggest optimizations to turn slow COLLSCAN operations into efficient IXSCAN operations.
  2. AI Judge Evaluate (LLM-as-a-judge)
    • Click "AI Judge Evaluate" on any trace span to instantly open the Chatbot. The Gemini Agent analyzes the raw input and output, scores its safety and optimality, and provides a human-readable explanation of what the database command actually did.
  3. Context-Aware AI Chat Sidebar
    • Forget writing complex aggregation pipelines manually. Just ask the agent: "Show me the top 5 products by revenue grouped by category in a pie chart."
    • The agent securely translates natural language to MongoDB aggregations via the MongoDB MCP and instantly visualizes the result using ECharts—right in your browser.
  4. One-Click Index Optimization
    • Every collection view features an "Optimize Index" magic button that instantly triggers the AI to evaluate your current schema, query usage, and indexes to suggest performance enhancements.
  5. "Vibe" Aesthetics (Minimalist & Modern)
    • Built on Vue 3 and Vite, it drops the clunky Java-like interfaces of legacy tools in favor of a sleek, glassmorphic, responsive, dark-mode native dashboard.
  6. Full-Stack Feature Parity
    • Supports Document CRUD, dynamic BSON parsing, complex schema analysis, mass deletion, multi-database connection management, and comprehensive zip-based Backup & Restore workflows.

🏗️ Architecture & Technology Stack

VibeMongo Admin runs as a unified containerized service hosting both backend API services and frontend assets.

graph TD
    subgraph Client [Browser - Vue 3 SPA]
        Dashboard[Dashboard & Explorer]
        Chat[Agent Chat Sidebar]
        Observability[Observability Charts]
    end

    subgraph Container [Docker Container - Node 20 Server]
        Express[Express.js Server]
        SQLite[(SQLite DB - Connections)]
        NeDB[(NeDB - Telemetry & Stats)]
        ADK[Google ADK Agent]
        MongoService[MongoService Driver]
    end

    subgraph External [External APIs & Subprocesses]
        Gemini[Gemini API / Vertex AI]
        MCP[mongodb-mcp-server subprocess]
        MongoDB[(MongoDB Database)]
        Phoenix[Arize Phoenix Cloud]
    end

    Client -- HTTPS & SSE --> Express
    Express -- Connection Profile --> SQLite
    Express -- Query DB --> MongoService
    MongoService --> MongoDB
    Express -- Telemetry Data --> NeDB

    ADK -- Model Calls --> Gemini
    ADK -- Execute Tool --> MCP
    MCP --> MongoDB
    
    Express -- Traces/Spans --> Phoenix
    ADK -- Telemetry Evaluator --> Phoenix
    Express -- Serve Static Assets --> Client

VibeMongo Architecture Diagram

Core Integration (The Tri-Partner Architecture)

  • Frontend (UI/UX): Vue 3 (Composition API) with Vite, styled with modern Element Plus and ECharts. We built a dynamic parsing engine that reads specific JSON blocks outputted by the AI agent to render interactive components on the fly.
  • Brain (Google Cloud Agent & Gemini): We utilized the Google Agent Development Kit (ADK) and Google's highly capable Gemini 3.1 Flash-Lite model on Vertex AI to act as the central reasoning engine.
  • Execution (MongoDB MCP): To bridge the AI agent with MongoDB securely, we integrated the official MongoDB MCP Server (mongodb-mcp-server). The Agent leverages this standardized Model Context Protocol to introspect schemas and execute aggregation pipelines dynamically based on the current active connection.
  • Observability & Evaluation (Arize Phoenix Cloud & MCP): We integrated the Arize Phoenix MCP and @arizeai/phoenix-otel to capture OpenTelemetry traces of both MongoDB operations and LLM reasoning. When the user requests an "AI Judge Evaluation" or "Ask AI to Optimize", the UI fetches the trace data and sends it back to the Gemini Agent to provide human-readable, step-by-step diagnostic feedback directly in the chat interface.

Technology Stack Components

Frontend (Client)

ComponentTechnologyRole / Description
FrameworkVue 3 + TypeScriptCore reactive Single Page Application (SPA) using Composition API
Build ToolViteUltra-fast Hot Module Replacement (HMR) and production build pipeline
UI LibraryElement PlusPremium component library for modern, dark-mode native dashboard layout
Charts & DatavizECharts, Chart.js, vue-echartsInteractive query results and performance metrics visualization
State ManagementPiniaModular, type-safe global client state stores
RoutingVue Router 4Client-side view routing & navigation guards
HTTP ClientAxiosRESTful API communication with the backend service
i18nvue-i18nMulti-language localization support
StylingSass (SCSS)CSS preprocessor for custom glassmorphic styling and smooth variables control

Backend (Server)

ComponentTechnologyRole / Description
RuntimeNode.js 20+Fast, cross-platform JavaScript server runtime
FrameworkExpress 4Lightweight REST API endpoint router
LanguageTypeScriptStrong typing for clean, maintainable backend business logic
Database DriverMongoDB Node.js Driver v6Native driver for direct database management and CRUD operations
Observability DBNeDB (@seald-io/nedb)Lightweight, embedded datastore for telemetry, server stats & monitoring
Connection StoreSQLite (sqlite3)Encrypted, server-side storage of MongoDB connection profiles
File HandlerMulterMultipart form parser for uploading zip-based database backups

AI Agent & Observability Layer

ComponentTechnologyRole / Description
Agent SDK@google/adk v1Google Agent Development Kit for AI agent orchestration and tool execution
LLM ModelGemini (via Vertex AI / Google AI Studio)High-performance reasoning engine for natural-language-to-BSON query translation
Tool TransportMCP stdio subprocessSecure local execution of the mongodb-mcp-server command via standard I/O
MCP SDK@modelcontextprotocol/sdkNode SDK implementing Model Context Protocol JSON-RPC standard
Database Toolsmongodb-mcp-server (npx)Official MongoDB MCP tools for schema introspection and pipeline execution
Telemetry Tools@arizeai/phoenix-mcpTrace monitoring integration for real-time trace analysis & DB-Guardian
Observability APMArize Phoenix Cloud & OpenTelemetryTelemetry spans capture for LLM evaluations, tracing bottlenecks & query debugging

📸 Screenshots

Authentication & Connections

Login Connections Add Connection Edit Connection Delete Connection

Dashboard & Databases

Connection Dashboard Database Explorer Create Database Rename Database Drop Database Add Database User Database AI Analysis Loading Database AI Analysis Dashboard Database AI Analysis Charts MongoDB Atlas Cluster Metrics

Collections

Collections View Create Collection Rename Collection Drop Collection Collection Schema Analyzer

Documents

Query Console Quick Filter Builder Documents Table View Documents List View Document Editor Insert New Document

Indexes

Collection Indexes Create Index Edit Index

Backup & Restore

Backup Database Restore Database

AI Agent (MongoDB MCP)

Agent Welcome Agent Thinking State Agent Databases Response Agent Autocomplete Support Agent Schema Analysis Agent Data Query Agent Data Visualization (Sidebar) Agent Data Visualization (Full Page) Agent Index Analysis Agent Index Recommendations Agent Index Comparison

DB-Guardian (AI-Driven SRE)

DB-Guardian Diagnostic Report DB-Guardian Resolution & Performance Chart

AI Judge (Observability & Telemetry)

AI Judge Trace Evaluation AI Judge Diagnostic Summary AI Judge SRE Recommendations AI Judge Optimization Suggestion AI Judge Caching Strategy Implementation AI Judge Trace Evaluation Trigger AI Judge Bottleneck Analysis Response AI Judge Predictive Scaling Model AI Judge Detailed Evaluation Prompt AI Judge SRE Breakdown Operation AI Judge SRE Output & Score Assessment AI Judge Security & Privacy Audit AI Judge Data Leakage Assessment

Observability Dashboard & Telemetry

SRE Health Assessment & Real-Time Metrics Resident Memory vs Database Connections Arize Phoenix Observability Telemetry Trace Latency Percentiles & Average Annotation Score Model Token Usage Analysis All Trace Spans Table Logs DB-Guardian Active Spans Alert Banner Traces filtered list view Trace Detail Explorer Parent Span Trace Detail Explorer Sub-span Data Trace Attributes Table Drawer Trace Gantt-Waterfall Bottleneck Visualizer Arize Phoenix Portal Tracing Dashboard Arize Phoenix Portal Metrics Graphs Arize Phoenix Portal Trace Detail View Arize Phoenix Portal Tool Output Detail

Personalization (i18n & Theming)

Internationalization Light Mode Dark Mode

GCP Cloud Run Production Deployment

GCP Cloud Run Observability Metrics GCP Cloud Run Live Logs GCP Cloud Run Revisions List GCP Cloud Run Deploy Container Configuration


🏗️ Quick Start (Local Development)

Prerequisites

  • Node.js >= 20
  • pnpm >= 9
  • MongoDB (Atlas or local instance)
  • Google Cloud Project with Vertex AI API enabled

1. Clone and install

git clone https://github.com/camtruong512/vibe-mongo-admin.git
cd vibe-mongo-admin
pnpm install

2. Configure environment

cp .env.example .env
# Edit .env with your credentials (see Backend Guide for details)

3. Run development servers

pnpm run dev
# Client → http://localhost:3000
# Backend → http://localhost:4000

🔑 Environment Variables Summary

VariableRequiredDescription
PORTYesBackend server port (default: 4000)
HOSTYesBackend host (default: 0.0.0.0)
PASSWORDYesAdmin dashboard password
VITE_API_URLYesFrontend → Backend URL
GOOGLE_CLOUD_PROJECTYesGCP Project ID for Vertex AI
GOOGLE_CLOUD_LOCATIONYesVertex AI region (e.g. global, us-central1)
GOOGLE_GENAI_USE_VERTEXAIYesSet to 1 to use Vertex AI
GOOGLE_API_KEYConditionalGoogle API Key (if not using Vertex AI)
AGENT_MODELYesGemini model name (e.g. gemini-3.1-flash-lite)
ENCRYPTION_KEYYes32-char key for encrypting MongoDB connection strings
NODE_ENVYesdevelopment or production
PHOENIX_PROJECT_NAMEYesArize Phoenix project name for tracing (Get from https://app.phoenix.arize.com)
PHOENIX_COLLECTOR_ENDPOINTYesArize Phoenix collector endpoint (E.g. https://app.phoenix.arize.com/s/your_workspace)
PHOENIX_API_KEYYesArize API Key for tracing (Get from https://app.phoenix.arize.com/settings?tab=api-keys)

👤 Developer

👤 Supporter


📝 License

This project is licensed under the MIT License.

See the LICENSE file for more information.

Ver o original no GitHub

Bom para

Relacionados