Pythia MCP
An MCP server that interfaces with the Lilith library to analyze Higgs boson phenomenology and LHC experimental data. It enables AI assistants to constrain new physics theories by calculating likelihoods and signal strengths for various particle physics scenarios.
README
<div align="center">
<!-- Animated Header --> <img src="https://capsule-render.vercel.app/api?type=waving&color=gradient&customColorList=24,25,26&height=200§ion=header&text=๐ฎ%20PYTHIA&fontSize=80&fontColor=fff&animation=twinkling&fontAlignY=35&desc=Higgs%20Boson%20Phenomenology%20MCP%20Server&descAlignY=55&descSize=18"/>
<br/>
<!-- Badges Row 1 --> <p> <a href="https://modelcontextprotocol.io"><img src="https://img.shields.io/badge/MCP-Server-00d4aa?style=for-the-badge" alt="MCP Server"/></a> <a href="https://home.cern"><img src="https://img.shields.io/badge/CERN-LHC_Data-0033a0?style=for-the-badge" alt="CERN"/></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-GPL_v3-blue?style=for-the-badge" alt="License"/></a> <a href="#"><img src="https://img.shields.io/badge/Physics-Research-9b59b6?style=for-the-badge" alt="Physics"/></a> </p>
<!-- Badges Row 2 --> <p> <img src="https://img.shields.io/badge/TypeScript-โ-3178c6?style=flat-square&logo=typescript&logoColor=white" alt="TypeScript"/> <img src="https://img.shields.io/badge/Python-3.6+-3776ab?style=flat-square&logo=python&logoColor=white" alt="Python"/> <img src="https://img.shields.io/badge/Lilith-Interface-ff6b6b?style=flat-square" alt="Lilith"/> <img src="https://img.shields.io/badge/Higgs_Boson-125_GeV-gold?style=flat-square" alt="Higgs"/> <img src="https://img.shields.io/badge/Claude_Desktop-Ready-blueviolet?style=flat-square&logo=anthropic" alt="Claude"/> </p>
<br/>
<!-- Tagline Box --> <table> <tr> <td>
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ โ
โ ๐ฎ Named after the Oracle of Delphi, Pythia brings the power of โ
โ particle physics to your AI assistant โ enabling Claude to โ
โ constrain new physics from LHC Higgs boson measurements. โ
โ โ
โ โ๏ธ Interface: Lilith library for Higgs phenomenology โ
โ ๐ Data: ATLAS + CMS signal strength measurements โ
โ ๐ฌ Physics: Beyond Standard Model constraints โ
โ โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
</td> </tr> </table>
<br/>
<!-- Quick Links --> ๐ Quick Start ยท โ๏ธ Physics ยท ๐ง Tools ยท ๐ Examples ยท ๐ Citations
<br/>
</div>
<br/>
๐๏ธ Built on Lilith
<div align="center">
โ ๏ธ IMPORTANT: This project is a wrapper around Lilith-2, a powerful Python tool developed by Sabine Kraml and collaborators at LPSC Grenoble. All physics calculations are performed by Lilith โ Pythia simply provides an MCP interface.
โญ Star the Original Lilith Repository and cite the Lilith papers in your research!
</div>
<br/>
<br/>
๐ฏ What is Pythia?
<table> <tr> <td width="50%">
๐ฌ The Challenge
New physics theories predict
modified Higgs couplings...
But how do we test them
against LHC data?
โ Complex calculations
โ Multiple decay channels
โ Statistical combinations
โ Expert knowledge required
</td> <td width="50%">
โ Pythia Solution
Ask Claude in plain English:
"What constraints does LHC
data place on a two-Higgs
doublet model?"
โ
Lilith handles the math
โ
Signal strengths computed
โ
Constraints calculated
โ
Results explained clearly
</td> </tr> </table>
<br/>
<br/>
โ๏ธ Physics Background
<div align="center">
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ โ
โ THE 125 GeV HIGGS BOSON โ
โ โ
โ Discovery: July 4, 2012 at CERN's Large Hadron Collider โ
โ โ
โ โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ
โ โ โ โ
โ โ Production Modes Decay Channels โ โ
โ โ โโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโ โ โ
โ โ โข ggF (gluon fusion) โข H โ ฮณฮณ (diphoton) โ โ
โ โ โข VBF (vector boson) โข H โ ZZ* โ 4โ โ โ
โ โ โข WH, ZH (associated) โข H โ WW* โ โฮฝโฮฝ โ โ
โ โ โข ttH (top associated) โข H โ bbฬ, ฯฯ, ฮผฮผ โ โ
โ โ โ โ
โ โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ
โ โ
โ Signal Strength: ฮผ = ฯ_observed / ฯ_SM_predicted โ
โ โ
โ ฮผ = 1 โ Standard Model โ โ
โ ฮผ โ 1 โ New Physics! ๐ โ
โ โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
</div>
<br/>
๐ Reduced Couplings (ฮบ-Framework)
<div align="center">
| Coupling | SM Value | Description |
|---|---|---|
| C_V | 1.0 | Coupling to W and Z bosons |
| C_t | 1.0 | Coupling to top quark |
| C_b | 1.0 | Coupling to bottom quark |
| C_ฯ | 1.0 | Coupling to tau lepton |
| C_g | 1.0 | Effective coupling to gluons (loop) |
| C_ฮณ | 1.0 | Effective coupling to photons (loop) |
</div>
<br/>
<br/>
๐ Quick Start
๐ฆ Installation
# Clone the repository
git clone https://github.com/consigcody94/pythia-mcp.git
cd pythia-mcp
# Install Node.js dependencies
npm install
# Build TypeScript
npm run build
# Ensure Python dependencies are installed
pip install numpy scipy
โก Claude Desktop Configuration
Add to your claude_desktop_config.json:
{
"mcpServers": {
"pythia": {
"command": "node",
"args": ["/path/to/pythia-mcp/dist/index.js"],
"env": {
"LILITH_DIR": "/path/to/pythia-mcp/lilith",
"PYTHON_CMD": "python3"
}
}
}
}
โ Verify Installation
cd lilith
python run_lilith.py userinput/example_couplings.xml
<br/>
<br/>
๐ง Available Tools
๐ฌ Core Analysis
<div align="center">
| Tool | Description |
|---|---|
compute_likelihood |
Calculate -2 log(L) for BSM scenarios |
compute_sm_likelihood |
Get Standard Model reference |
compute_pvalue |
Calculate p-value for model comparison |
scan_1d |
1D parameter scan with likelihood profile |
scan_2d |
2D scan for contour plots |
</div>
๐ Data Management
<div align="center">
| Tool | Description |
|---|---|
list_experimental_data |
List datasets in Lilith database |
search_hepdata |
Search HEPData for new measurements |
fetch_hepdata_record |
Download specific HEPData record |
get_latest_higgs_data |
Fetch latest from all sources |
</div>
๐งช Physics Models
<div align="center">
| Tool | Description |
|---|---|
analyze_2hdm |
Two-Higgs-Doublet Model analysis |
analyze_singlet_extension |
Higgs singlet extension |
get_sm_predictions |
SM cross sections & branching ratios |
convert_to_signal_strength |
Convert couplings to ฮผ values |
</div>
<br/>
<br/>
๐ Usage Examples
Example 1: Standard Model Check
"Use Pythia to compute the Standard Model likelihood and tell me if the Higgs data is consistent with the SM."
Example 2: BSM Scenario
"Calculate the likelihood for a model where the Higgs coupling to top quarks is 0.9 and to vector bosons is 1.1"
{
"mode": "couplings",
"Ct": 0.9,
"CV": 1.1
}
Example 3: 2HDM Analysis
"Analyze a Type-II 2HDM with tan(ฮฒ) = 2 and sin(ฮฒ-ฮฑ) = 0.99"
{
"type": "II",
"tanBeta": 2,
"sinBetaMinusAlpha": 0.99
}
Example 4: Parameter Scan
"Scan the CV-CF plane from 0.8 to 1.2 with 50 steps each"
{
"param1": {"name": "CV", "min": 0.8, "max": 1.2, "steps": 50},
"param2": {"name": "CF", "min": 0.8, "max": 1.2, "steps": 50}
}
<br/>
<br/>
๐ Data Sources
<div align="center">
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ โ
โ โโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโ โ
โ โ ๐ฌ LILITH DB โ โ ๐ HEPDATA โ โ ๐ CERN OPEN โ โ
โ โ โโโโโโโโโโโโโโ โ โ โโโโโโโโโโโโโโ โ โ โโโโโโโโโโโโโโ โ โ
โ โ Run 1 (7+8TeV) โ โ Official HEP โ โ Real collision โ โ
โ โ Run 2 (13TeV) โ โ data archive โ โ data & MC โ โ
โ โ ATLAS + CMS โ โ CERN/Durham โ โ analysis code โ โ
โ โโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโ โ
โ โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
</div>
<br/>
<br/>
๐๏ธ Architecture
pythia-mcp/
โโโ ๐ฆ src/
โ โโโ index.ts # MCP server entry point
โ โโโ tools/ # Tool implementations
โ
โโโ ๐ฎ lilith/ # Lilith library (bundled)
โ โโโ run_lilith.py # Main entry point
โ โโโ userinput/ # XML input templates
โ โโโ data/ # Experimental database
โ
โโโ ๐ฆ dist/ # Compiled output
โโโ ๐ package.json
โโโ ๐ tsconfig.json
<br/>
<br/>
๐ Citations & Acknowledgments
๐ Required Citations
If you use Pythia for research, you MUST cite Lilith:
@article{Bernon:2015hsa,
author = "Bernon, Jรฉrรฉmy and Dumont, Bรฉranger",
title = "{Lilith: A tool for constraining new physics from Higgs measurements}",
journal = "Eur. Phys. J. C",
volume = "75",
pages = "440",
year = "2015",
doi = "10.1140/epjc/s10052-015-3645-9",
eprint = "1502.04138",
archivePrefix = "arXiv"
}
@article{Kraml:2019sis,
author = "Kraml, Sabine and others",
title = "{Lilith-2: Improved precision constraints}",
year = "2019",
eprint = "1908.03952",
archivePrefix = "arXiv"
}
๐ Special Thanks
<div align="center">
| Sabine Kraml & Lilith Team | LPSC Grenoble |
| ATLAS & CMS Collaborations | Higgs measurements |
| HEPData Team | Durham/CERN |
| Anthropic | MCP Protocol |
</div>
<br/>
<br/>
๐ References
<div align="center">
| Resource | Link |
|---|---|
| Lilith-2 | github.com/sabinekraml/Lilith-2 |
| Lilith Paper | arXiv:1502.04138 |
| HEPData | hepdata.net |
| CERN Open Data | opendata.cern.ch |
| LHC Higgs XS WG | twiki.cern.ch |
</div>
<br/>
<br/>
๐ License
<div align="center">
GNU General Public License v3.0
This project and Lilith are licensed under GPL v3 - see LICENSE for details.
</div>
<br/>
<div align="center">
<img src="https://capsule-render.vercel.app/api?type=waving&color=gradient&customColorList=24,25,26&height=100§ion=footer"/>
<br/>
๐ฎ Pythia โ Seeking Truth in the Higgs Sector
<br/>
"The Higgs boson is the key to understanding the origin of mass in the universe." <br/> โ Peter Higgs
<br/>
Made with dedication to open science and particle physics research
<br/>
</div>
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.