Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SLD MCP Server Extract A_LR from hadronic events"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for public SLD data analysis and electroweak measurements.
This server exposes agent-callable tools for working with the public SLD release: the modernized parquet translation of the 1996–1998 polarized SLD e+e- Z-pole dataset described in An AI-ready, Polarized Electron-Positron Collision Dataset (arXiv:2606.00224).
This server uses the SLD Resurrection analysis codebase.
This server exposes tools in four categories:
Data Inspection
Selection & Cutflow
Physics Computation
Plotting
Related MCP server: CERN ROOT MCP Server
This server currently supports:
inspection of SLD parquet shards and bank structure
selection preset discovery and cutflow reporting
hadronic event selection and A_LR extraction
leptonic asymmetry measurements
visible mass, event-shape, angular, and weak-mixing summary plots
This server does not yet expose OmniLearned embedding or classifier workflows.
Install in editable mode from the repository root:
pip install -e .
Start the MCP server with:
sld_mcp_server
This server assumes:
local access to the public SLD parquet dataset
a working installation of SLD Resurrection
Python 3.10 or newer
This server cannot be deployed
Machine-readable utilities and datasets for AI agents.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Calibrated world model for AI agents. 40 tools: world state, markets, trading. Kalshi + Polymarket.
Gateway between LLM agents and world data through eight tools and a bundled endpoint catalog.
