
Meta Prompt Mcp
io.github.kapillamba4由 GitHub 帳號 kapillamba4 發布v1.0.11更新於 Oct 24, 2026
MCP server providing official Google and Anthropic prompting guides for meta-prompt generation.
概覽
一個本機 MCP 伺服器,提供內建的 Google 與 Anthropic 提示詞指南,讓助理依據官方最佳實務撰寫中繼提示詞與系統提示詞。
- 可以做什麼
- 從內建的 markdown 檔案讀取 Google 提示詞指南(涵蓋技巧、最佳實務與 LLM 設定)以及 Anthropic 關於思維鏈、多範例提示與延伸思考的指南,全程不進行網路呼叫。助理閱讀這些指南後,可據此針對特定任務提出改進建議或挑選合適技巧。
- 適用情境
- 適合在撰寫或調整代理的系統提示詞與中繼提示詞時使用,或當你希望提示詞建議立基於 Google 與 Anthropic 的方法論而非憑空猜測時使用。
- 執行需求
- 透過 stdio 在本機執行;可用 uvx 或 pip 安裝 Python 套件 meta-prompt-mcp。日常使用不需 API 金鑰或網路存取。選用的基準測試目標需要 OPENROUTER_API_KEY。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Meta Prompt Mcp,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
Meta-Prompt MCP
Instant access to Google and Anthropic's official prompting guides within your LLM workflow—optimized for crafting high-quality meta-prompts and system prompts.
What It Does
Meta-Prompt MCP is an MCP server that surfaces official prompting best practices from Google and Anthropic directly within your LLM workflow. Instead of searching documentation or guessing how to instruct an LLM, you can query expert guides on-demand.
This is especially valuable when crafting meta-prompts (system prompts for agents) or optimizing your own prompting strategies. By grounding your prompts in proven methodology, you'll generate more effective, well-structured outputs.
How It Works
Your MCP host (Claude Desktop, Cursor, etc.) communicates with the server via stdio. When you ask for a guide, the server retrieves it from bundled markdown files—no API calls, no latency.
Key Features
get_google_guide— Retrieves Google's comprehensive prompting guide covering techniques, best practices, and LLM configurationget_anthropic_guide— Retrieves Anthropic's guide on chain-of-thought, multishot prompting, and extended thinking- Zero dependencies — Runs entirely offline with bundled guides; no API keys or network calls required
Validation
We ran a benchmark comparing prompts generated with and without guide access across 5 diverse tasks. An independent judge LLM scored each on Clarity, Specificity, Structure, Effectiveness, and Overall quality (1–10 scale).
To reproduce the benchmark:
Quick Start
1. Install
The package ships with bundled markdown guides — no API keys or setup needed.
2. Configure Your MCP Host
Claude Desktop
Add to your claude_desktop_config.json:
Cursor
Add to your MCP settings:
Claude Code
Run the following command in your terminal:
Usage
Query the guides while crafting your prompts. Examples:
- "I'm building a code reviewer agent. Reference the Google guide to help me write a better system prompt."
- "Based on the Anthropic guide, suggest improvements to this prompt for better reasoning."
- "What technique from the guides would work best for this task?"
The LLM reads the guides and uses that knowledge to give you more informed suggestions and feedback on your prompts.
Development
Available Commands
Project Structure
Contributing
Issues, feature requests, and contributions welcome. Please open an issue on GitHub.
License
MIT
來源:README.md,提交 3b8d06a
工具
0版本歷史
1- v1.0.11最新Sep 16, 2026
評分
已滿足適用檢查項的 50%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分