AI Optimizer MCP
AI Optimizer MCP 🧠🔧 - Multi-Task MCP Server
Entwickelt von Barack Ndenga ♥️
Details
Multi-Task MCP Server für VSCode/Cursor, CLI, autonome Agenten. KI-Codeoptimierung + Tests + erweiterbar.
Transportwege: Stdio (VSCode), Subprocess, HTTP (zukünftig)
Anwendungsfälle: VSCode-Chat, Agenten-Schleifen, CI/CD, Remote-Server
Sicherheit: Umgebungsvariablen, Sandbox-Ausführung
Related MCP server: VegaMCP
Manifest (Multi-Task-Fähigkeiten)
🛠️ 3+ Tools: Code testen/optimieren/Zielvorgaben (+erweiterbar)
🔌 VSCode/Cursor: natives mcp.json
🖥️ CLI Standalone:
ai-optimizer-mcp run🤖 Agenten: examples/agent.py Schleife
⚙️ Multi-Env: Lokal/Dev/Prod via .env
📊 Speicher/Historie: JSON persistent
🔄 Iterative Schleifen: Automatische Verbesserung
Multi-Plattform-Konfiguration
1. VSCode/Cursor (Empfohlen)
Datei .vscode/mcp.json (Multi-Server):
{
"servers": {
"ai-optimizer": {
"command": "python",
"args": ["-m", "ai_optimizer_mcp.server"]
},
"ai-optimizer-dev": {
"command": "python",
"args": ["-m", "ai_optimizer_mcp.cli", "run", "--dev"]
}
}
}Multi-Task: Server im Chat wechseln!
2. CLI / Skripte / Agenten
ai-optimizer-mcp run # Stdio server (pipes)
ai-optimizer-mcp run --dev # Debug
ai-optimizer-mcp --install-mcp # Print mcp.json3. Autonome Agenten / 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})Voraussetzungen (.env)
cp .env.example .env
# OPENAI_API_KEY=sk-...
# OBJECTIVE="Your custom goal"Multi-Task-Nutzung
VSCode Chat:
use_mcp_tool("ai-optimizer", "run_tests", ...)CLI Pipe:
echo code | ai-optimizer-mcp runAgenten-Schleife:
python examples/agent.pyCI/CD: Subprocess in GitHub Actions/Jenkins
Beispiel Tool-Antwort:
run_tests → "Tests passed: score=4/4 (f(2)=4)"
generate_improvement → "def f(x): return 2 * x"Multi-Env-Fehlerbehebung
VSCode: Fenster nach mcp.json neu laden
Kein API-Schlüssel: ValueError → .env prüfen
Timeout:
TEST_TIMEOUT=10in .envSpeicher:
rm memory.jsonLogs:
--devoderLOG_LEVEL=DEBUG
Entwicklung
pip install -e .[dev]
pre-commit install
pytestMCP-Tools (Erweiterbar)
Tool | Argumente | Anwendungsfall |
|
| VSCode/CLI Code testen |
|
| Automatisch optimieren |
| - | Ziel in jedem Kontext lesen |
Apache 2.0 - Multi-Task bereit! VSCode, CLI, Agenten, CI. Tragen Sie bei!
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