AI Optimizer MCP
AI Optimizer MCP 🧠🔧 - Servidor MCP Multitarea
Desarrollado por Barack Ndenga ♥️
Detalles
Servidor MCP multitarea para VSCode/Cursor, CLI y agentes autónomos. Optimización de código mediante IA + pruebas + extensible.
Transportes: Stdio (VSCode), subprocess, HTTP (futuro)
Casos de uso: Chat de VSCode, bucles de agentes, CI/CD, servidores remotos
Seguridad: Variables de entorno, ejecución en sandbox
Related MCP server: VegaMCP
Manifiesto (Capacidades multitarea)
🛠️ 3+ Herramientas: Prueba/optimización de código/objetivo (+extensibles)
🔌 VSCode/Cursor: mcp.json nativo
🖥️ CLI independiente:
ai-optimizer-mcp run🤖 Agentes: bucle en examples/agent.py
⚙️ Entorno múltiple: Local/dev/prod mediante .env
📊 Memoria/Historial: JSON persistente
🔄 Bucles iterativos: Auto-mejora
Configuración multiplataforma
1. VSCode/Cursor (Recomendado)
Archivo .vscode/mcp.json (servidores múltiples):
{
"servers": {
"ai-optimizer": {
"command": "python",
"args": ["-m", "ai_optimizer_mcp.server"]
},
"ai-optimizer-dev": {
"command": "python",
"args": ["-m", "ai_optimizer_mcp.cli", "run", "--dev"]
}
}
}Multitarea: ¡Cambia de servidor en el chat!
2. CLI / Scripts / Agentes
ai-optimizer-mcp run # Stdio server (pipes)
ai-optimizer-mcp run --dev # Debug
ai-optimizer-mcp --install-mcp # Print mcp.json3. Agentes autónomos / Subprocess
# examples/agent.py
import asyncio
from mcp.client.stdio import stdio_client
async def agent_loop():
async with stdio_client(command=["python", "-m", "ai_optimizer_mcp.server"]) as client:
# Multi-task calls
score = await client.call_tool("run_tests", {"code_snippet": code})
improved = await client.call_tool("generate_improvement", {"code": code, "test_result": score})Requisitos previos (.env)
cp .env.example .env
# OPENAI_API_KEY=sk-...
# OBJECTIVE="Your custom goal"Uso multitarea
Chat de VSCode:
use_mcp_tool("ai-optimizer", "run_tests", ...)CLI Pipe:
echo code | ai-optimizer-mcp runBucle de agente:
python examples/agent.pyCI/CD: Subprocess en GitHub Actions/Jenkins
Ejemplo de respuesta de herramienta:
run_tests → "Tests passed: score=4/4 (f(2)=4)"
generate_improvement → "def f(x): return 2 * x"Solución de problemas en entornos múltiples
VSCode: Recarga la ventana después de modificar mcp.json
Sin clave API: ValueError → Comprueba .env
Tiempo de espera:
TEST_TIMEOUT=10en .envMemoria:
rm memory.jsonRegistros:
--devoLOG_LEVEL=DEBUG
Desarrollo
pip install -e .[dev]
pre-commit install
pytestHerramientas MCP (Extensibles)
Herramienta | Argumentos | Caso de uso |
|
| Probar código en VSCode/CLI |
|
| Auto-optimización |
| - | Leer objetivo en cualquier contexto |
Apache 2.0 - ¡Listo para multitarea! VSCode, CLI, Agentes, CI. ¡Contribuye!
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for building and testing AI agents with multi-model experimentation and insights.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA lightweight MCP server that enhances AI agents with tools for codebase analysis, task delegation to sub-agents, multi-agent coordination through chatrooms, and project todo management.-
- AlicenseCqualityDmaintenanceA production-grade MCP server providing an autonomous AI agent swarm, persistent semantic memory, browser automation, multi-model reasoning, and 78+ tools for AI-first testing and development.63MIT
- AlicenseNot gradedqualityCmaintenanceMCP server that enables AI coding agents to communicate, share state, and coordinate work in real time via MCP tools or REST API.107 npm9MIT
- AlicenseNot gradedqualityBmaintenanceMulti-agent AI orchestrator that runs parallel coding agents in isolated sessions with self-improving intelligence, exposed via an MCP server for task execution and management.MIT