openmc-validator-mcp
An MCP server that provides pre-flight validation and post-processing tools for OpenMC Monte Carlo transport simulations, catching common authoring mistakes before jobs hit the HPC queue.
README
openmc-validator-mcp
An MCP (Model Context Protocol) server that provides pre-flight validation and post-processing tools for OpenMC Monte Carlo transport simulations. Catch common authoring mistakes before the job hits the HPC queue — eliminate the costly "submit → queue → fail → fix → resubmit" loop.
Features
The server exposes 14 tools across four categories:
Validators (5) — Catch mistakes at authoring time
| Tool | What it checks |
|---|---|
validate_materials |
Nuclide name typos, negative density, ao/wo fraction mixing, L2 round-trip |
validate_geometry |
Unclosed surface references, unknown universes/cells, DAGMC path validity |
validate_settings |
Batch/population sanity, source definition completeness, D-T energy check |
validate_tallies |
Energy bin ordering, mesh axis validity, score whitelist |
validate_model |
End-to-end model validation; optional openmc --geometry-debug subprocess |
Cross-Checks (3) — Spot interface mismatches
| Tool | What it checks |
|---|---|
check_cross_section_library |
Nuclide + temperature availability in cross_sections.xml |
check_energy_filter_coverage |
Energy filter upper edge vs. source max energy (e.g. 14.1 MeV) |
check_tally_filter_consistency |
Tally cell filters vs. geometry cells, mesh extent boundaries |
Converters (2) — Bridge OpenMC to downstream codes
| Tool | What it does |
|---|---|
convert_spectrum_openmc_to_fispact |
OpenMC energy tally → FISPACT-II ARBI spectrum file |
extract_tally_summary |
statepoint.h5 → structured JSON (mean / std / rel_err) |
Template & Material Catalog (4) — Browse pre-built OpenMC templates
| Tool | What it does |
|---|---|
list_templates |
List all available OpenMC model templates by category |
get_template |
Retrieve a specific template with all files (geometry, materials, settings) |
list_materials |
List all pre-defined material definitions across templates |
get_material |
Look up a specific material by name, get nuclide composition |
Requires OPENMC_TEMPLATES_DIR environment variable pointing to an
openmc-templates repository.
Error Code System
40+ structured error codes across 7 domains (MAT-*, SET-*, TAL-*, GEO-*,
XS-*, EFC-*, TFC-*, MOD-*, ENV-*), each with severity, trigger
description, and suggested fix. See docs/error-codes.md.
Installation
Requires Python ≥ 3.10.
# Basic install (L1 validation only, no OpenMC API required)
pip install openmc-validator
# Editable install for development
pip install -e ".[dev]"
For L2 validation (material round-trip through OpenMC API, geometry-debug):
# OpenMC is only available via conda-forge
conda create -n openmc-env -c conda-forge python=3.11 openmc
conda activate openmc-env
pip install -e ".[dev]"
Without OpenMC, L2-dependent checks degrade gracefully with ENV-W001 warnings.
Quick Start
As an MCP Server
Add to your VS Code mcp.json:
{
"servers": {
"openmc-validator": {
"command": "openmc-validator",
"args": []
}
}
}
See examples/mcp-config.json for a complete
example with OPENMC_CROSS_SECTIONS env.
Programmatic Use
from openmc_validator.validators.materials import validate_materials
from openmc_validator.schemas import MaterialSpec, NuclideSpec
spec = MaterialSpec(
name="Water",
density=1.0,
density_units="g/cm3",
nuclides=[
NuclideSpec(name="H1", fraction=2.0, fraction_type="ao"),
NuclideSpec(name="O16", fraction=1.0, fraction_type="ao"),
],
)
report = validate_materials([spec])
print(report.passed, report.issues)
Documentation
| Document | Description |
|---|---|
docs/tool-reference.md |
Full API reference for all 14 tools |
docs/error-codes.md |
Index of all validation error/warning codes |
docs/changelog.md |
Version history |
examples/agent-integration.md |
Using the server with AI coding agents |
Project Layout
src/openmc_validator/
schemas/ # pydantic input/output models
validators/ # 5 validator modules
crosschecks/ # 3 cross-check modules
converters/ # 2 converter modules
utils/ # subprocess helpers, logging
server.py # FastMCP entry point
tests/
unit/ # pure-python unit tests (no openmc binary required)
integration/ # end-to-end MCP protocol tests
fixtures/
valid/ # positive examples
invalid/ # negative examples (expected to fail validation)
Contributing
Contributions are welcome! Please see CONTRIBUTING.md for
development setup, test instructions, and pull request guidelines.
This project follows the Contributor Covenant Code of
Conduct. Security vulnerabilities should be reported as described in
SECURITY.md.
License
MIT — see LICENSE for details.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。