How does the auto‑detection achieve 70% token savings?
It automatically detects specific functions, classes, or components from natural language prompts, reducing context noise by 85% and targeting only the relevant elements.
@jacv888
基本情報
Aider-MCP-Upgraded is a production-grade multi-agent AI coding system that combines Desktop Commander (DC) investigation capabilities with Aider's implementation power. Features 70%+ token reduction, modular architecture, and intelligent workflow automation through strategic agen
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"aider-mcp-upgraded": {
"command": "python",
"args": [
"app/scripts/update_claude_config.py"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
A production-grade multi‑agent AI coding system that combines Desktop Commander investigation capabilities with Aider’s implementation power. It features 70%+ token reduction, modular architecture, and intelligent workflow automation for developers using Claude Desktop.
Install via the one‑command setup script (./app/scripts/setup.sh), then configure a .env file with API keys for OpenAI, Google, and/or Anthropic. Add the MCP servers to Claude Desktop and use natural language prompts to trigger the multi‑agent workflow. Specific environment variables like AIDER_MODEL_HARD, MAX_COST_PER_TASK, and ENABLE_AUTO_TARGET_DETECTION control model routing, cost limits, and auto‑detection.
It automatically detects specific functions, classes, or components from natural language prompts, reducing context noise by 85% and targeting only the relevant elements.
OpenAI (GPT‑4.1 series), Google (Gemini 2.5 Pro/Flash), and Anthropic (Claude Sonnet 4) are configurable via API keys. Models are routed by task complexity (hard/medium/easy/simple) and framework type (Django, React, Next.js, etc.).
Claude Desktop, Python, and the UV package manager are required. The setup script auto‑detects paths and configures the environment. API keys for at least one supported provider are needed.
Desktop Commander investigates files and identifies exact elements, then Aider implements with auto‑detection, and Claude validates results. Handoff is seamless, with conflict prevention and parallel execution support.
Yes. Environment variables like `
This is a very basic implementation of an Mcp-Reasoning-Server for Cursor AI .
Search, understand, reproduce, and improve an idea with ease
Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM through the aiswmm runtime, reusable Skills, and MCP interfaces, with QA verification, provenance tracking, calibration support, and Codex,
An MCP server that allows you to run TypeScript, JavaScript, and Python code in a sandbox on your local machine using the Deno® sandbox. This server provides a controlled environment for executing code with explicit permission controls.
AI assistant integration for n8n workflow automation through Model Context Protocol (MCP). Connect Claude Desktop, ChatGPT, and other AI assistants to n8n for natural language workflow management.
コメント