Kerykeion MCP Server
Enables astrological chart generation including natal charts, synastry, transits, composite charts, and planetary returns using the Kerykeion library. Supports multiple output formats (text, SVG, PNG) and customizable themes, house systems, and languages.
README
Kerykeion MCP Server
An MCP (Model Context Protocol) server for astrological chart generation using the Kerykeion library. Compatible with Claude Desktop and ChatGPT Desktop.
Features
- Natal Charts - Birth chart generation with planetary positions, aspects, and house placements
- Synastry Charts - Relationship compatibility analysis between two people
- Transit Charts - Current transits to natal positions
- Composite Charts - Midpoint composite for relationship dynamics
- Planetary Returns - Solar, Lunar, and other planetary return charts
- Event Charts - Charts for specific moments (electional, horary)
- Current Positions - Quick lookup of current planetary positions
Output Formats
- Text - AI-readable descriptions optimized for LLM interpretation
- SVG - Vector chart images saved to files (path returned in response)
- PNG - High-resolution (1600px) raster images (requires
cairosvg)
Installation
Using uv (Recommended)
cd kerykeion-mcp
uv sync
Using pip
pip install -e .
System Dependencies for PNG Support
For PNG conversion, you need Cairo graphics library:
# Ubuntu/Debian
sudo apt install libcairo2-dev
# macOS
brew install cairo
# Windows - See cairosvg documentation
Usage
Development Mode (MCP Inspector)
uv run mcp dev src/kerykeion_mcp/server.py
Then open the MCP Inspector at http://localhost:8000/mcp to test tools.
Claude Desktop Configuration
Add to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"kerykeion-charts": {
"command": "uv",
"args": [
"run",
"--directory", "/path/to/kerykeion-mcp",
"python", "-m", "kerykeion_mcp.server"
]
}
}
}
Or install directly:
uv run mcp install src/kerykeion_mcp/server.py --name "Kerykeion Charts"
ChatGPT Desktop Configuration
Important: ChatGPT requires HTTPS URLs for MCP connectors. You'll need to tunnel your local server.
-
Start the server with SSE transport:
uv run python -m kerykeion_mcp.server --sseServer runs at
http://localhost:8000/sse -
Create an HTTPS tunnel using ngrok (or similar):
ngrok http 8000You'll get a URL like:
https://abc123.ngrok-free.app -
Add to ChatGPT:
- Enable Developer Mode: Settings → Connectors → Advanced → Developer mode
- Add MCP Server URL:
https://abc123.ngrok-free.app/sse
Available Tools
| Tool | Description |
|---|---|
generate_natal_chart |
Create a birth chart |
generate_synastry_chart |
Relationship compatibility analysis |
generate_transit_chart |
Current or specified transits to natal |
generate_composite_chart |
Midpoint composite for a couple |
generate_planetary_return |
Solar/Lunar returns |
generate_event_chart |
Chart for any specific moment |
get_current_positions |
Current planetary positions (text only) |
get_aspects |
Get natal chart aspects without images |
get_synastry_aspects |
Get inter-chart aspects for compatibility |
Common Parameters
All chart tools accept:
- lat/lng: Coordinates (positive N/E, negative S/W)
- tz_str: IANA timezone (e.g., "Europe/Rome", "America/New_York")
- theme: "classic", "light", "dark", "strawberry", "dark-high-contrast"
- language: "EN" (default), "IT", "FR", "ES", "PT", "CN", "RU", "TR", "DE", "HI"
- house_system: "P" (Placidus), "W" (Whole Sign), "K" (Koch), "M" (Morinus), etc.
- output_format: "text", "images", or "all"
- output_dir: Custom directory to save chart images (optional)
- chart_style: "full" (default), "wheel_only", or "aspect_grid"
Response Format
All chart tools return a compact response (~1KB) with file paths:
{
"status": "success",
"summary": "Chart generated successfully. SVG: /path/to/file.svg, PNG: /path/to/file.png",
"chart_type": "Natal",
"subject_name": "Test",
"text": "AI-readable chart analysis...",
"svg_path": "/home/user/.kerykeion_charts/natal_test_20260106.svg",
"png_path": "/home/user/.kerykeion_charts/natal_test_20260106.png",
"output_dir": "/home/user/.kerykeion_charts"
}
Note: Chart content is saved to files rather than returned inline. This keeps responses small and prevents MCP clients from showing "Tool result too large" messages. The AI assistant can read SVG files directly if needed for embedding.
Embedding Charts in Claude Artifacts
Method 1: Read SVG File (Recommended)
The AI assistant can read the SVG file directly from svg_path and embed it:
<html>
<body>
<!-- SVG content read from svg_path file -->
</body>
</html>
Result: Interactive, scalable vector chart in artifact.
Method 2: PNG with File Path
Response includes png_path for local file linking:

Download the markdown file - image renders from local path.
Example Usage
Ask Claude or ChatGPT:
"Generate a natal chart for someone born June 15, 1990 at 2:30 PM in Rome (lat: 41.9028, lng: 12.4964, timezone: Europe/Rome)"
"Create a synastry chart comparing Person A (born Jan 1, 1985 in NYC) and Person B (born Dec 25, 1987 in London)"
"What are the current planetary transits to my natal chart?"
Prompts
The server includes pre-defined prompts to guide conversations:
- natal_chart_prompt - Template for creating natal charts
- synastry_prompt - Template for relationship compatibility
- transit_prompt - Template for transit analysis
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。