ROOT MCP Server

omazapa/root_mcp_server

Brings CERN's ROOT data analysis framework into the MCP ecosystem through two tools: root_python for executing Python with PyROOT automatically in scope, and root_cpp for running C++ via ROOT's cling interpreter. Everything runs in-process with automatic error detection, console logging of executed code, and support for TCanvas graphics. The server handles histogram creation, statistical analysis, and physics computations without needing HTTP endpoints or external APIs. Reach for this when you want LLMs to generate and execute ROOT analysis code directly, whether you're fitting distributions, plotting particle physics data, or prototyping analyses interactively. Works with VS Code Copilot Chat or any MCP client over stdio transport.

GitHub stars

1

tools

2

transport

STDIO

last updated

Nov 22, 2025

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

README.md

root_mcp_server: MCP Server for ROOT

Model Context Protocol server for executing Python and C++ code with PyROOT

---

Minimal MCP (Model Context Protocol) server that allows LLMs and other MCP clients to execute Python and C++ code directly using PyROOT, without HTTP endpoints or external APIs.

Features

---

View the full README on GitHub

Show full README.md