Skip to main content

prompt-optimizer-mcp v1.1.1

作者 / Author: goodie1972 GitHub: https://github.com/goodie1972/prompt-optimizer PyPI: https://pypi.org/project/prompt-optimizer-mcp/1.1.1/


简介 / Introduction

中文: 一个 ZCode 提示词优化 MCP 工具包,提供 optimize_prompt MCP 工具和 /optimize 命令,通过 LLM 优化提示词,使其更清晰、更具体、更可执行。

English: A ZCode prompt optimizer MCP package that provides the optimize_prompt MCP tool and /optimize command. It uses LLM to refine prompts, making them clearer, more specific, and more actionable.


安装 / Installation

中文

pip install prompt-optimizer-mcp

English

pip install prompt-optimizer-mcp

在 ZCode 中使用 / Usage in ZCode

中文

安装后在 ZCode 的 MCP 配置中添加:

English

After installation, add the following to your ZCode MCP configuration:

{
  "mcpServers": {
    "prompt-optimizer": {
      "command": "prompt-optimizer-mcp",
      "env": {}
    }
  }
}

配置 / Configuration

中文

在 ~/.zcode/mcp/prompt-optimizer/.env 中设置 API Key:

OPTIMIZE_API_KEY=你的key
OPTIMIZE_BASE_URL=https://你的地址/v1
OPTIMIZE_MODEL=模型名

或直接设置环境变量:

AGNES_API_KEY=...
# 或 / or
OPENAI_API_KEY=...

English

Set your API Key in ~/.zcode/mcp/prompt-optimizer/.env:

OPTIMIZE_API_KEY=your-api-key
OPTIMIZE_BASE_URL=https://your-endpoint/v1
OPTIMIZE_MODEL=model-name

Or set environment variables directly:

AGNES_API_KEY=...
# or
OPENAI_API_KEY=...

使用 / Usage

中文

作为 MCP 工具: AI 在对话中自动调用 optimize_prompt 工具:

optimize_prompt(prompt="写一个Python脚本读取CSV")
# 返回:写一个Python脚本,读取指定路径的CSV文件...

作为命令行工具: 启动 MCP 服务器:

prompt-optimizer-mcp

English

As an MCP tool: The AI automatically invokes the optimize_prompt tool during conversations:

optimize_prompt(prompt="Write a Python script to read a CSV file")
# Returns: Write a Python script that reads a CSV file from a specified path...

As a CLI tool: Start the MCP server:

prompt-optimizer-mcp

更新日志 / Changelog

v1.1.1

  • 中文: 文档更新为双语(中英文);添加 GitHub 和 PyPI 链接
  • English: Documentation updated to bilingual (Chinese/English); added GitHub and PyPI links

v1.1.0

  • 中文: 兼容 mcp 2.0.0(FastMCP → MCPServer);依赖更新:mcp>=2.0.0
  • English: Compatible with mcp 2.0.0 (FastMCP → MCPServer); dependency updated: mcp>=2.0.0

v1.0.0

  • 中文: 初始发布
  • English: Initial release


许可证 / License

MIT

Metadata

Release files for prompt-optimizer-mcp 1.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for prompt-optimizer-mcp 1.2.0
File Size Uploaded
prompt_optimizer_mcp-1.2.0.tar.gz 5.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for prompt-optimizer-mcp 1.2.0
File Interpreter ABI Platform
prompt_optimizer_mcp-1.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 11.6 kB

Release files / prompt_optimizer_mcp-1.2.0.tar.gz

Download URL prompt_optimizer_mcp-1.2.0.tar.gz
Size 5.2 kB
Tags Source
SHA-256 checksum
How to use checksums
0a32ab70fa6898f74a039bb9a4987929a6286732bab67be18d0990c9e55a5926
BLAKE2b-256 checksum
How to use checksums
c08fa69d8febe0982ef7a7b97655d50a508c10ef559992c687595f3361cfa228
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.2

Release files / prompt_optimizer_mcp-1.2.0-py3-none-any.whl

Download URL prompt_optimizer_mcp-1.2.0-py3-none-any.whl
Size 6.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a316a73bfcd6060f3dfed5558769cf4271540d13aeef0ab5f0be5a8df682a0a8
BLAKE2b-256 checksum
How to use checksums
ae668ff838a5e0bfb3daa7d6dcac19a729fbf2d2667acc9e1d087966a518b4bc
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.2

Release history Release notifications | RSS feed

This release

1.2.0 This release

2 release files

1.1.1

2 release files

1.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page