Pythia MCP is a server that wraps the Lilith-2 library, giving AI assistants access to Higgs boson phenomenology tools for constraining beyond-Standard-Model physics from LHC measurements.
Core Analysis
Compute likelihoods (-2 log L) for BSM scenarios using reduced couplings (κ-framework) or signal strengths
Compute SM reference likelihoods and p-values for statistical compatibility
Run 1D/2D parameter scans to profile likelihoods and generate contour plots
Experimental Data Management
Browse built-in ATLAS, CMS, and Tevatron datasets; inspect best-fit values, uncertainties, and correlations
Search and fetch records from HEPData by decay channel, production mode, year, or collaboration
Update the local database with new signal-strength publications; retrieve the latest Higgs data aggregated from HEPData and CERN Open Data
Physics Model Analysis
Analyze Two-Higgs-Doublet Models (Types I, II, Lepton-specific, Flipped) given tan(β) and sin(β−α)
Evaluate Higgs singlet mixing extensions with optional invisible branching ratios
Retrieve SM predictions for cross sections and branching ratios at 7–14 TeV
Convert reduced couplings to signal strengths across all production/decay modes
Validate Lilith XML input format without running a full calculation
CERN Open Data Integration
Search the CERN Open Data portal for Higgs-related datasets and analysis code
Retrieve record metadata and list downloadable files (with optional regex filtering)
Supported Parameters
Couplings: C_V, C_t, C_b, C_c, C_tau, C_mu, C_g, C_γ, C_Zγ
Production modes: ggH, VBF, WH, ZH, ttH, tH, bbH
Decay channels: γγ, ZZ, WW, bb, ττ, μμ, cc, Zγ, gg, invisible
Allows fetching and analyzing particle physics experimental data and records from the HEPData repository using INSPIRE identifiers.
Click on "Install 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., "@Pythia MCPWhat constraints does LHC data place on a two-Higgs doublet model?"
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.
Constrain beyond-Standard-Model physics from LHC Higgs measurements — directly from Claude.
Pythia wraps the Lilith library as an MCP server, giving AI assistants access to 28 particle physics analysis tools.
Getting Started • Tools • Examples • Architecture • Citations
Lilith Attribution — All physics calculations are performed by Lilith-2, developed by Sabine Kraml and collaborators at LPSC Grenoble. Pythia is an MCP interface layer. Please star the original repo and cite the Lilith papers in any research output.
Overview
The 125 GeV Higgs boson, discovered at CERN in 2012, is the cornerstone of electroweak symmetry breaking. Precision measurements of its couplings to other particles provide one of the most powerful probes for physics beyond the Standard Model (BSM).
Pythia bridges this frontier physics with conversational AI. Instead of manually running Python scripts and parsing XML, you ask Claude:
"What constraints does LHC data place on a Type-II two-Higgs-doublet model with tan(beta) = 2?"
Under the hood, Pythia generates validated XML input, invokes Lilith's likelihood engine against the full ATLAS + CMS dataset, and returns structured results — all through the Model Context Protocol.
Getting Started
Prerequisites
Requirement | Version |
Node.js | >= 18.0 |
Python | >= 3.6 |
NumPy + SciPy | latest |
Install
Configure Claude Desktop
Add to your claude_desktop_config.json:
Verify
You should see a -2log(likelihood) value printed to stdout.
Tools
Pythia exposes 28 tools organized into four categories.
Core Analysis
Tool | Description |
| Compute -2 log(L) for any BSM coupling or signal-strength scenario |
| Standard Model reference likelihood |
| P-value for model comparison against SM or best-fit |
| 1D parameter scan with likelihood profile (parallel execution) |
| 2D parameter scan for contour plots (parallel execution) |
Data Management
Tool | Description |
| Browse Lilith's built-in ATLAS/CMS/Tevatron datasets |
| Inspect a specific experimental XML measurement file |
| Query the HEPData repository for new results |
| Download a HEPData record by INSPIRE ID or record number |
| Check HEPData for new signal-strength publications |
| Aggregate latest measurements from HEPData + CERN Open Data |
Physics Models
Tool | Description |
| Two-Higgs-Doublet Model (Types I, II, Lepton-specific, Flipped) |
| Higgs singlet extension with mixing angle |
| SM cross sections and branching ratios at 7-14 TeV |
| Convert reduced couplings to signal-strength values |
| Validate Lilith XML input without running the full calculation |
| Library and database version information |
CERN Open Data
Tool | Description |
| Search the CERN Open Data portal |
| Retrieve record metadata by ID |
| List downloadable files for a record |
Examples
Check SM Consistency
"Compute the Standard Model likelihood and tell me if the Higgs data is consistent with the SM."
Test Modified Couplings
"Calculate the likelihood for C_t = 0.9, C_V = 1.1"
Two-Higgs-Doublet Model
"Analyze a Type-II 2HDM with tan(beta) = 2 and sin(beta - alpha) = 0.99"
Parameter Scan
"Scan the C_V–C_F plane from 0.8 to 1.2"
Physics Reference
Reduced Couplings (kappa-framework)
The kappa-framework parameterizes deviations from SM Higgs couplings as multiplicative modifiers:
Parameter | Description | SM Value |
C_V | Vector boson coupling (W, Z) | 1.0 |
C_t | Top quark coupling | 1.0 |
C_b | Bottom quark coupling | 1.0 |
C_c | Charm quark coupling | 1.0 |
C_tau | Tau lepton coupling | 1.0 |
C_mu | Muon coupling | 1.0 |
C_g | Effective gluon coupling (loop-induced) | 1.0 |
C_gamma | Effective photon coupling (loop-induced) | 1.0 |
Signal strength: μ = σ_obs / σ_SM. A value of μ = 1 is consistent with the Standard Model.
Supported Production & Decay Modes
Production: ggH, VBF, WH, ZH, ttH, tH, bbH
Decay: γγ, ZZ, WW, bb, ττ, μμ, cc, Zγ, gg, invisible
Architecture
Security
Input validation — All coupling, mass, and branching-ratio parameters are range-checked before use.
XML injection prevention — All user-supplied values are escaped before embedding in XML.
Path traversal protection — Dataset paths are resolved and verified against a base directory.
ReDoS prevention — User-supplied regex patterns are length-limited and checked for dangerous constructs.
API safety — HTTP requests enforce 30s timeouts, redirect depth limits, and response caching with TTL.
Subprocess limits — Python process output is capped at 1 MB to prevent memory exhaustion.
Development
Environment Variables
Variable | Default | Description |
|
| Path to Lilith installation |
|
| Python interpreter command |
Citations
If you use Pythia in research, you must cite the Lilith papers:
Acknowledgments
Sabine Kraml & Lilith Team | LPSC Grenoble — physics engine |
ATLAS & CMS Collaborations | Higgs boson measurements |
HEPData | Durham / CERN — data archive |
Anthropic | Model Context Protocol |
References
Resource | Link |
Lilith-2 source | |
Lilith paper | |
HEPData | |
CERN Open Data | |
LHC Higgs XS WG | |
Model Context Protocol |
License
GNU General Public License v3.0 — Pythia and the bundled Lilith library are both GPL-3.0 licensed.
"The Higgs boson is the key to understanding the origin of mass in the universe." — Peter Higgs
Built for open science and particle physics research.