gw150914 -signal-search
🌊 GW150914 MCP Signal Search: AI-powered gravitational wave detection using Model Context Protocol (MCP). Features optimization client, analysis server, and automated parameter exploration for LIGO data.
claude mcp add --transport stdio iphysresearch-gw150914-mcp-signal-search python mcp-server/gw_analysis_server.py \ --env LOG_DIR="data/logs/" \ --env DATA_PATH="data/" \ --env OPENAI_API_KEY="your-openai-api-key-here"
How to use
This MCP server pair provides gravitational wave analysis tools and an AI-assisted optimization client for GW150914 signal search. The GW Analysis Server exposes MCP endpoints for data fetching, matched-filter searches, multi-detector network analysis, and visualization of results. The Optimization Client uses an AI agent to steer the search over a 4D parameter space (mass1, mass2, right ascension, declination) by learning from historical results and current SNR feedback. Run the server to start analysis services, then launch the client to begin AI-guided parameter exploration. The system stores execution logs and results under data/logs and can visualize analysis outputs via the server’s plotting utilities.
How to install
Prerequisites:
- Python 3.9 or higher
- UV package manager (uv)
Installation steps:
- Install UV (if not already installed):
curl -LsSf https://astral.sh/uv/install.sh | sh
- Clone the repository and set up the project:
git clone <repository-url>
cd gw150914-mcp-signal-search
make setup
- Configure environment variables:
cp env.template .env
# Edit .env to set your OPENAI_API_KEY and any other needed vars
- Install dependencies (development):
make install-dev
- Run the demo or start components as needed:
# Start a server and client
make run-client SERVER_PATH=mcp-server/gw_analysis_server.py
# Or run the full demo
make demo
Additional notes
Notes and tips:
- Environment variables: set OPENAI_API_KEY for the optimization client. The server may also reference DATA_PATH and LOG_DIR to locate data and store logs.
- Data handling: strain data and results live under data/; matched_filter_records.jsonl contains optimization history.
- Logs: execution logs are saved under data/logs with timestamps for debugging.
- If you encounter port or path issues, ensure the working directory is the repository root and that the Python path includes the mcp-server directory.
- For production, consider separating the server and client into distinct processes or containers and redirect logs to a centralized location.
Related MCP Servers
Upsonic
Agent Framework For Fintech and Banks
scira -chat
A minimalistic MCP client with a good feature set.
mcp_on_ruby
💎 A Ruby implementation of the Model Context Protocol
chatgpt-app-typescript-template
ChatGPT app template using Pomerium, OpenAI Apps SDK and Model Context Protocol (MCP), with a Node.js server and React widgets.
mcp-chat-widget
Configure, host and embed MCP-enabled chat widgets for your website or product. Lightweight and extensible Chatbase clone to remotely configure and embed your agents anywhere.
agentmesh
🤖🕸️ Production-grade multi-agent orchestration framework powered by Pregel BSP. Build sophisticated AI workflows with parallel execution, state management, and observability.