npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@jiaqi.li/llm-tools

v1.0.1

Published

基于 Sentry MCP 的错误分析和修复工具,支持 Claude Code、Cursor 等 AI 工具

Readme

LLM Tools

基于 Sentry MCP 的智能错误分析和修复工具,让 AI 助手能够自动分析和修复 Sentry 上报的错误。

🌟 特性

  • 🔍 智能错误分析:自动从 Sentry 获取错误详情并进行深度分析
  • 🛠️ 自动错误修复:AI 辅助修复代码,减少人工调试时间
  • 🤖 多 AI 工具支持:支持 Claude Code、Cursor、Windsurf、Continue 等主流 AI 编程工具
  • 🎯 简单易用:通过斜杠命令快速调用,只需粘贴 Sentry URL
  • 🏢 自建 Sentry 支持:完美支持自建 Sentry 站点

📦 安装

无需安装! 直接使用 npx 运行:

# 交互式菜单
npx @jiaqi.li/llm-tools

# 或直接运行特定命令
npx @jiaqi.li/llm-tools setup-sentry     # 配置 Sentry MCP
npx @jiaqi.li/llm-tools setup-commands   # 配置 AI 工具

🚀 快速开始(仅需 2 步)

第一步:配置 Sentry MCP

npx @jiaqi.li/llm-tools setup-sentry

按照提示输入:

  • Sentry 站点地址(例如:sentry.tec-do.cnsentry.io
  • Sentry Access Token(从 Sentry 设置中获取,见下方说明)

配置完成后,重启你的 AI 工具(如 Claude Code)以使 MCP 配置生效。

第二步:配置 AI 工具命令

npx @jiaqi.li/llm-tools setup-commands

脚本会引导你:

  1. 选择要配置的 AI 工具(支持多选,空格选择,回车确认)
    • ✅ Claude Code
    • ✅ Cursor
    • ✅ Windsurf
    • ✅ Continue
  2. 输入项目根目录路径(默认为当前目录)

配置完成后,对应的命令文件会自动创建:

  • Claude Code → .claude/skills/
  • Cursor → .cursor/commands/
  • Windsurf → .windsurf/commands/
  • Continue → .continue/commands/

💡 使用方法

分析 Sentry 错误

在你的 AI 工具中输入:

/analyze-sentry-error https://sentry.tec-do.cn/organizations/your-org/issues/12345/

或者直接输入 Issue ID:

/analyze-sentry-error 12345

AI 会自动:

  1. 从 Sentry 获取错误详情
  2. 分析堆栈跟踪和错误上下文
  3. 定位问题代码位置
  4. 提供详细的分析报告,包括:
    • 📋 错误概要
    • 🔍 详细分析
    • 📍 问题定位
    • 💡 可能原因
    • 📊 影响评估
    • 🎯 修复建议

修复 Sentry 错误

在你的 AI 工具中输入:

/fix-sentry-error https://sentry.tec-do.cn/organizations/your-org/issues/12345/

AI 会:

  1. 分析错误
  2. 定位问题代码
  3. 提出修复方案并征求确认
  4. 自动修改代码
  5. 提供验证建议

📁 项目结构

llm-tools/
├── scripts/
│   ├── setup-sentry-mcp.js      # Sentry MCP 配置脚本
│   └── setup-commands.js         # AI 工具命令配置脚本
├── prompts/
│   ├── analyze-sentry-error.md   # 错误分析 prompt 模板
│   └── fix-sentry-error.md       # 错误修复 prompt 模板
├── package.json
└── README.md

🔧 进阶配置

手动配置 Sentry MCP

如果你更喜欢手动配置,可以直接编辑 Claude Code 的配置文件:

macOS/Linux: ~/.config/claude-code/config.json Windows: %APPDATA%/Claude Code/config.json

添加以下配置:

{
  "mcpServers": {
    "sentry": {
      "command": "npx",
      "args": [
        "@sentry/mcp-server@latest",
        "--access-token=YOUR_ACCESS_TOKEN",
        "--host=YOUR_SENTRY_HOST"
      ]
    }
  }
}

获取 Sentry Access Token

  1. 登录你的 Sentry 账号
  2. 进入 SettingsAccountAPIAuth Tokens
  3. 点击 Create New Token
  4. 选择权限:至少需要 event:readproject:read
  5. 创建并复制 token

🤝 贡献

欢迎提交 Issue 和 Pull Request!

📄 许可证

MIT

🙏 致谢

本项目灵感来源于 OpenSpec,感谢他们提供的优秀实践