Pythia

Provides an MCP interface to Lilith-2 for constraining Higgs sector new physics using LHC data.
  • typescript

0

GitHub Stars

typescript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "consigcody94-pythia-mcp": {
      "command": "node",
      "args": [
        "/path/to/pythia-mcp/dist/index.js"
      ],
      "env": {
        "LILITH_DIR": "/path/to/pythia-mcp/lilith",
        "PYTHON_CMD": "python3"
      }
    }
  }
}

You can run a local MCP server that connects Lilith-2 data constraints to your Higgs phenomenology workflow. This server lets you perform physics analyses, manage data sources, and execute common analysis tasks from a single, repeatable interface while keeping Lilith-2 calculations at the core.

How to use

To use the MCP server, run it locally and connect your MCP client or UI to the provided runtime. The server operates as a local process that interfaces with Lilith-2 to perform Higgs-physics calculations and constraint evaluations. You will configure the client to start the server process and pass the appropriate runtime arguments and environment variables.

How to install

Prerequisites: you need Node.js for the MCP server runtime and Python for Lilith-2 components. Ensure Python 3 is available on your system and that Node.js is installed for the local server execution.

Step 1 — Clone the MCP project repository.

Step 2 — Install Node.js dependencies.

# Clone the repository
git clone https://github.com/consigcody94/pythia-mcp.git
cd pythia-mcp

# Install Node.js dependencies
npm install

# Build TypeScript to JavaScript
npm run build

# Ensure Python dependencies are available
pip install numpy scipy

MCP runtime configuration

Configure the local MCP runtime in your client by providing a stdio-based server command and its arguments. The runtime is started as a local process, and you supply the exact command and environment needed to run the server.

{
  "mcpServers": {
    "pythia": {
      "type": "stdio",
      "name": "pythia",
      "command": "node",
      "args": ["/path/to/pythia-mcp/dist/index.js"],
      "env": {
        "LILITH_DIR": "/path/to/pythia-mcp/lilith",
        "PYTHON_CMD": "python3"
      }
    }
  }
}

Available tools

compute_likelihood

Calculate the -2 log(L) value for Beyond the Standard Model scenarios to assess fit quality against Higgs data.

compute_sm_likelihood

Compute the Standard Model reference likelihood for comparison with alternative models.

compute_pvalue

Calculate the p-value for model comparison to quantify statistical significance.

scan_1d

Perform a 1D parameter scan with a likelihood profile to explore favored regions.

scan_2d

Perform a 2D parameter scan to generate contour plots of parameter space.

list_experimental_data

List datasets available in the Lilith database for quick reference.

search_hepdata

Search HEPData for new measurements relevant to Higgs phenomenology.

fetch_hepdata_record

Download a specific HEPData record for local analysis.

get_latest_higgs_data

Fetch the latest Higgs measurements from all sources.

analyze_2hdm

Analyze a Two-Higgs-Doublet Model scenario.

analyze_singlet_extension

Analyze a Higgs sector extension with a singlet field.

get_sm_predictions

Retrieve Standard Model cross sections and branching ratios.

convert_to_signal_strength

Convert couplings into signal strength modifiers (μ values).

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational