The root_mcp_server is a minimal 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.
From the registry: ROOT-based MCP server exposing root_python and root_cpp tools (stdio transport).

$ pip install -e .https://github.com/omazapa/root_mcp_serverPlease install the `root-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **ROOT (CERN)** — ROOT 6.x or later with PyROOT enabled must be installed and sourced (thisroot.sh). (https://root.cern/install/)
- **Python** — Python 3.10+ required. (https://python.org)
- **Install package** — Clone repo and install in editable mode. Run: `pip install -e .` (https://github.com/omazapa/root_mcp_server)
Canonical MCP server config (stdio transport):
- command: `root_mcp_server`
- args: []
Note: Execute Python and C++ code with PyROOT (CERN ROOT data analysis framework). Requires ROOT installation with PyROOT enabled. Tools: root_python and root_cpp.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.