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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.