mcpField
H
HYRR

HYRR

Local
exoma-ch.github.ioScience & Education0Updated 4w ago
RepositoryVisit website

About HYRR

HYRR is an MCP server for querying radio-isotope production and related beam calculations. Its tools are implemented in Rust, with a thin Python package for distribution.

Key features

  1. 01Simulate isotope production
  2. 02List materials and reaction channels
  3. 03Retrieve decay and stopping-power data
  4. 04Compare simulations and energy budgets
  5. 05Get isotope production curves

Use cases

  1. 01Estimate isotope production for a charged-particle beam
  2. 02Review reaction channels for available materials
  3. 03Compare simulation results and stack energy budgets

MCP support

Exposes radio-isotope production query tools to MCP clients over stdio JSON-RPC, including simulation, decay-data, and stopping-power operations.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "exoma-ch-hyrr": {
      "command": "uvx",
      "args": [
        "hyrr-mcp"
      ],
      "env": {
        "HYRR_DATA": "<HYRR_DATA>",
        "HYRR_LIBRARY": "<HYRR_LIBRARY>"
      }
    }
  }
}
Run commanduvx hyrr-mcp
Environment variables to set
HYRR_DATAnucl-parquet data directory. Unset: the matching data release is fetched once into ~/.hyrr/nucl-parquet
HYRR_LIBRARYNuclear data library id, e.g. tendl-2023-iso (default) or endfb-8.1

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypihyrr-mcp0.22.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

hyrr-mcp

HYRR MCP server — stdio JSON-RPC for radio-isotope production queries.

Listed in the official MCP Registry as io.github.exoma-ch/hyrr.

Install and register with Claude Code:

claude mcp add hyrr -- uvx hyrr-mcp

The first invocation downloads the wheel (or builds from source if no wheel exists for your platform); subsequent runs are instant.

Data resolution priority: --data-dir arg → HYRR_DATA env → sibling nucl-parquet/ → ~/.hyrr/nucl-parquet.

The tools surface (simulate, list_materials, list_reaction_channels, get_decay_data, compare_simulations, get_stack_energy_budget, get_stopping_power, get_isotope_production_curve) is implemented in Rust in hyrr-core::mcp; this package is a thin PyO3 wrapper used purely for distribution.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.