io.github.w8s/w8s-astro-mcp
编码与调试by w8s
基于 SQLite 的占星工具,支持本命盘、transits、ingress 预测、aspects、composite 与 Davison 盘。
什么是 io.github.w8s/w8s-astro-mcp?
基于 SQLite 的占星工具,支持本命盘、transits、ingress 预测、aspects、composite 与 Davison 盘。
README
w8s-astro-mcp
Personal astrological MCP server — natal charts, transits, forecasting, and relationship charts backed by a queryable SQLite database.
Features
- 🔭 Swiss Ephemeris precision — planetary positions via pysweph; optional high-precision file download
- 🗂️ Multi-profile — manage charts for yourself, family, and friends
- 📜 Persistent history — every transit lookup auto-logged to SQLite; query by date, planet, or sign
- 🔗 Relationship charts — composite and Davison charts for any group of 2+ people
- 🗓️ Event & electional tools — cast charts for any moment; scan windows for auspicious times
Quick Start
1. Install uv if you don't have it — see the uv installation guide for your platform.
2. Add to your Claude Desktop config:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"w8s-astro-mcp": {
"command": "uvx",
"args": ["w8s-astro-mcp"]
}
}
}
3. Restart Claude Desktop, then create your profile:
"Create an astro profile for me — my name is [Name], born [YYYY-MM-DD] at [HH:MM] in [City, State]."
That's it. Everything is stored in ~/.w8s-astro-mcp/astro.db (macOS/Linux) or %USERPROFILE%\.w8s-astro-mcp\astro.db (Windows).
Installation
Recommended: uvx (no install required)
uvx pulls the package from PyPI and runs it in an isolated environment automatically. Use the config above.
Alternative: pip
pip install w8s-astro-mcp
Then use "command": "w8s-astro-mcp" (no args) in your Claude Desktop config.
Requirements
- Python 3.10+
- uv (for
uvxmethod) or pip - Claude Desktop (or any MCP-compatible client)
Use Cases
Get started:
"Create an astro profile for me — my name is [Name], born [YYYY-MM-DD] at [HH:MM] in [City, State]."
"Show me my natal chart."
Daily practice:
"What are my transits for today?"
"When was Mercury last retrograde?"
"What major transits are coming up in the next 90 days?"
Relationships:
"Create a profile for my partner, born [YYYY-MM-DD] at [HH:MM] in [City, State]."
"Create a connection called 'Us' and show me our synastry."
"Calculate a Davison chart for us."
Events & planning:
"Cast a chart for the moment we got married — [date] at [time] in [city]."
"Find auspicious times to sign a contract next month — Moon not void, Mercury direct."
History & research:
"When was Jupiter last in Taurus?"
"Show me all my transit lookups from last month."
Documentation
| Doc | Contents |
|---|---|
| docs/ARCHITECTURE.md | Directory structure, full tool list, data flow, design decisions |
| docs/DATABASE_SCHEMA.md | Full ERD, all models, example SQL queries |
| docs/ROADMAP.md | Phase history and planned work |
| docs/TESTING_MCP.md | How to configure Claude Desktop and smoke-test the server |
Contributing & Development
See AGENTS.md for the development workflow, testing commands, branch strategy, and release checklist.
Questions & Bugs
Open an issue on GitHub.
License
常见问题
io.github.w8s/w8s-astro-mcp 是什么?
基于 SQLite 的占星工具,支持本命盘、transits、ingress 预测、aspects、composite 与 Davison 盘。
相关 Skills
网页构建器
by anthropics
面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。
✎ 在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。
前端设计
by anthropics
面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。
✎ 想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。
网页应用测试
by anthropics
用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。
✎ 借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。
相关 MCP Server
GitHub
编辑精选by GitHub
GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。
✎ 这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。
Context7 文档查询
编辑精选by Context7
Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。
✎ 它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。
by tldraw
tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。
✎ 这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。