NOVTRIQ Engineering
27 deterministic engineering compliance and calculation tools for the built environment (data-centre PUE and EED, EPBD, NIS2, Eurocode, UAE compliance), callable by AI agents via MCP and REST API. Free tier; every result cites the governing standard.
README
NOVTRIQ Engineering Intelligence MCP
An MCP (Model Context Protocol) server exposing 27 engineering intelligence tools for data centres and critical facilities, building energy and carbon, UK building regulations, Eurocode structural and cost, cyber and certification, and UAE compliance.
This repository is the open, self-hostable catalogue face of the NOVTRIQ MCP. It advertises the full tool set so any MCP client or aggregator can discover it, and it forwards tool execution to the authoritative hosted endpoint. The engineering calculators themselves run on the hosted service.
- Hosted endpoint:
https://api.novtriq.tech/mcp(streamable-http, keyless free tier) - Transport: JSON-RPC 2.0 over HTTP
- Tools: 27
- Provider: NOVTRIQ, UK engineering intelligence
Use the hosted server directly
Most clients should point straight at the hosted endpoint. Example MCP client config:
{
"mcpServers": {
"novtriq-engineering": {
"url": "https://api.novtriq.tech/mcp"
}
}
}
The free tier is keyless (5 requests/minute, 500/month per address). Higher tiers and API keys are available at https://novtriq.tech/eaas.
Run this catalogue server locally
pip install -r requirements.txt
uvicorn server:app --host 0.0.0.0 --port 8080
Or with Docker:
docker build -t novtriq-engineering-mcp .
docker run -p 8080:8080 novtriq-engineering-mcp
Then:
curl -s -X POST http://localhost:8080/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
initialize, tools/list, resources/list and prompts/list are answered locally.
tools/call is forwarded to the hosted endpoint (override with the
NOVTRIQ_MCP_UPSTREAM environment variable).
Tool catalogue
Data centres and critical facilities
calculate_pue (IEC 30134-2 / ASHRAE TC 9.9), estimate_cooling_load (CIBSE Guide B2 /
ASHRAE 90.1), thermal_load, eed_datacentre_pack (EU 2023/1791 Art.12, Reg 2024/1364)
Building energy, carbon and EPC
assess_epbd_score (EU 2024/1275), calculate_carbon (CIBSE TM65 / RICS WLCA),
building_carbon_footprint (CRREM), sap_sbem_precheck (UK SAP 10.3 / SBEM),
mees_checker, heatpump_heatloss (BS EN 12831 / MCS), digital_renovation_passport,
building_readiness
UK building regulations
part_o_overheating (Approved Document O), part_s_ev (Approved Document S),
uk_planning_checker (GPDO 2015)
Structural and cost
eurocode_beam_designer (EC3 / EC2), eurocode_column_checker (EC3),
eu_cost_benchmarking, get_technical_dd_quote (RICS / CIBSE), roi_calculator
Cyber and certification
check_nis2_readiness (EU 2022/2555), dgnb_bim_readiness (ISO 19650),
contractor_vetting
UAE
check_uae_bim_compliance (Dubai Circular 196, ISO 19650), check_uae_cybersecurity
(NESA / Dubai ISR / CBUAE / TDRA), check_grid_feasibility_uae (DEWA / ADDC / SEWA /
FEWA), uae_climate_ghg (Federal Decree-Law No. 11 of 2024)
The full JSON Schema for every tool is in tools.json.
Notes
Tool outputs are indicative engineering estimates and should be validated by a qualified engineer against current standards and site specific data.
License
MIT. See LICENSE.
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。