이 프로젝트는 종이 "Meta-Prompting : Task-Agnostic Scaffolding으로 언어 모델을 강화하는 "Meta-Prompting** 기법의 구현입니다.

그것의 핵심에, 이 MCP는 복잡한 체제 없이 동적인 다 시약 체계로 표준 언어 모형 (LM)를 개조합니다. 그것은 LM가 2개의 중요한 역할을 채택합니다:

1. ** 지휘자 **: 복잡한 문제를 분석하는 고수준 프로젝트 매니저는, 더 작은 논리적인 subtasks로, 그(것)들을 위임하고.
2. ** Expert**: 특수 대리인 (예: “Python Programmer,” “Code Reviewer,” “Creative Writer”)는 지휘자가 각 하위 작업을 수행하기 위해 "consulted"입니다.

마법은이 전체 협업 워크플로가 single LM 내에서 시뮬레이션됩니다. 지휘자와 전문가는 정교한 체계에 의해 인도된 가동의 다른 형태이고, 더 튼튼한 정확한 해결책에 모형을, 행위, 그리고 자기critique 그것의 방법을 허용하. AI 전문가의 자동화된 팀과 함께, 모든 모델에 의해 구동.

데모

시작하기

##1. 저장소를 복제

첫째로, clone 당신의 국부적으로 기계에 이 저장소.

##2. 설치 uv

Meta Prompt MCP

This project is an implementation of the Meta-Prompting technique from the paper “Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding”.

At its core, this MCP transforms a standard Language Model (LM) into a dynamic, multi-agent system without the complex setup. It works by having the LM adopt two key roles:

1. The Conductor: A high-level project manager that analyzes a complex problem, breaks it down into smaller, logical subtasks, and delegates them.
2. The Expert: Specialized agents (e.g., “Python Programmer,” “Code Reviewer,” “Creative Writer”) that are “consulted” by the Conductor to execute each subtask.

The magic is that this entire collaborative workflow is simulated within a single LM. The Conductor and Experts are different modes of operation guided by a sophisticated system prompt, allowing the model to reason, act, and self-critique its way to a more robust and accurate solution. It’s like having an automated team of AI specialists at your disposal, all powered by one model.

Demo

Getting Started

1. Clone the Repository

First, clone this repository to your local machine.

git clone https://github.com/tisu19021997/meta-prompt-mcp-server.git .
cd meta-prompt-mcp-server

2. Install uv

This project uses uv, an extremely fast Python package manager from Astral. If you don’t have it installed, you can do so with one of the following commands.

Note: use which uv to know the path of your uv installation.

macOS / Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

Windows (PowerShell):

powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

For more details, see the official uv installation guide.

Usage

To use this Meta Prompt MCP server, you need to configure your client (e.g., Cursor, Claude Desktop) to connect to it. Make sure to replace the placeholder paths with the actual paths on your machine.

Cursor

Add the following configuration to your mcp.json settings:

"meta-prompting": {
  "command": "path/to/your/uv",
  "args": [
    "--directory",
    "path/to/your/meta-prompt-mcp",
    "run",
    "mcp-meta-prompt"
  ]
}

Claude Desktop

Add the following configuration to your claude_desktop_config.json settings:

"meta-prompting": {
  "command": "path/to/your/uv",
  "args": [
    "--directory",
    "path/to/your/meta-prompt-mcp",
    "run",
    "mcp-meta-prompt"
  ]
}

Activating the Meta-Prompt Workflow