MCP.Market

Helionyx MCP server

by Jayzilva·io.github.Jayzilva/helionyx·v0.3.0
No reviews yet

Size hybrid solar PV, wind, battery, diesel and grid systems: hourly simulation, NPC ranking.

B83/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

0 stars132 downloads/wk

Reviews

Write one

Nobody has reviewed Helionyx yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Helionyx tools (22, 8 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • cancel_jobwrite action

    Cancel a queued or running job.

  • compare_runs

    Side-by-side sizes and key metrics of several runs (e.g. native vs REopt), with differences.

  • compute_bill

    Monthly and annual bill for a load with no system (baseline), or for import/export series.

  • create_scenariowrite action

    Combine site, loads, resource, grid/tariff, components and search space into a scenario. Unset fields take pack defaults; call validate_scenario next to see them.

  • create_sitewrite action

    Register a site (location, time zone and country pack). Returns site_id.

  • explain_runwrite action

    Structured facts about one design: NPC breakdown and shares, top cost drivers, binding constraints, dispatch statistics, differences from the next design or base case, and the most uncertain inputs.

  • export_homer_csvwrite action

    Write HOMER-importable load and resource series (8,760 rows) plus a parameter sheet.

  • export_reportwrite action

    Write a client report as Markdown or Excel: scenario, assumptions, top designs, cost breakdown, monthly table, sensitivities, provenance and disclaimer.

  • fetch_resource

    Get one year of hourly GHI, temperature and wind for a site, aligned to local civil time. Returns summary statistics only; the hourly series is available as a resource.

  • get_job_status

    Poll a job: state (queued, running, completed, failed, cancelled, interrupted), progress %, ETA, run_id.

  • get_monthly_summary

    Twelve months of energy flows and, for grid-connected runs, the bill before and after.

  • get_pareto_front

    Designs on the Pareto front of NPC, annual CO2 and capacity shortage, including designs that break a constraint (flagged), to show cost versus emissions versus reliability trade-offs.

  • get_results

    Ranked feasible designs with sizes and key metrics, the base case, provenance and disclaimer. The full table is the resource hnx://runs/{run_id}/results.csv.

  • get_sensitivity_results

    Optimal design for each sweep value and the NPC elasticity at the base point.

  • get_tariff

    Show a tariff's charge structure, TOU periods, export schemes, provenance and staleness warnings.

  • import_timeseries

    Import a measured load or resource series from CSV (one year, 15/30/60-minute resolution), or extend at least four weeks of measured load to a full year.

  • list_components

    Browse the component library: technical parameters, costs, currency, cost year and source.

  • list_tariffs

    Browse the tariff pack (utility, category, effective dates, export schemes).

  • run_optimizationwrite action

    Start an asynchronous run that simulates every candidate for 8,760 hours and ranks feasible ones. Returns job_id and run_id; poll get_job_status, then call get_results.

  • run_sensitivitywrite action

    Re-optimise the scenario for each value (or each pair of values in a two-variable grid) and compute NPC elasticities. Returns job_id and batch_id; then call get_sensitivity_results.

  • synthesize_load

    Build an 8,760-hour load from pack archetypes, optionally calibrated to monthly bills.

  • validate_scenario

    Check a scenario: errors block a run, warnings do not; assumptions list every value with its origin (user, pack_default or system_default), source and date.

Public scan report

scanner v0.1.10 · 2026-10-13 · same rubric, same numbers if you re-run it

no findings
  • Code scan88 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 6 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Helionyx compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
83/100
higher than 65% of 48,255 servers
Tools
22
the typical server has 7
Tools that change things
36%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
132
more than 69% of 12,191 servers with a package

What its tools let an agent do: 13 read · 3 create · 3 change · 1 delete · 2 run or deploy

Install Helionyx in Claude Code, Cursor or VS Code

claude mcp add helionyx -- uvx helionyx
Add to Cursor

What the publisher says

From the Helionyx repository's README, as published. We do not edit it. Read it on GitHub

Helionyx

Size hybrid energy systems by talking to your AI assistant. Helionyx is an open-source Model Context Protocol (MCP) server that sizes solar PV, wind, battery storage, diesel generator and grid-connected systems. It runs the classic techno-economic workflow:

  1. simulate every candidate design hour by hour for a full year;
  2. discard designs that break your constraints;
  3. rank the rest by net present cost (NPC), with payback, LCOE, bills and emissions.

The assistant never invents numbers. It asks scoping questions, calls deterministic tools and explains the results; every figure comes from a solver run with a run ID that anyone can reproduce. Use it for pre-feasibility studies, client proposals, rural electrification planning, teaching and cross-checking other tools.

Why Helionyx

life-cycle economics, tariffs with TOU, demand charges and export schemes, grid outages.

  • Grounded answers: the solver produces every number; the assistant only explains them.
  • Complete method: hourly dispatch (load following, cycle charging, TOU grid strategy),

reliability, multi-year load growth with staged expansion.

  • Beyond a single answer: sensitivity grids, Pareto trade-offs between cost, CO₂ and

HOMER-ready time series and Excel reports.

  • Cross-checked: compare against REopt, MicroGridsPy and SAMA from the same scenario.
  • Open and local: Apache-2.0, runs on your machine, works offline with bundled data, exports

Get started

Pick the way you use AI tools. Each one takes about a minute.

Then ask, for example:

Size a PV and battery system for a 60-room hotel in Negombo on the CEB hotel tariff. We have

about 1,200 m² of usable roof.

The quickstart walks through a first study in under ten minutes.

Where to find Helionyx

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Helionyx: common questions

Is Helionyx MCP server safe?
Mostly: it is graded B (83/100). Read the Helionyx safety report
How do I install Helionyx?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Helionyx need an API key?
Yes. The registry entry asks for HNX_REOPT_API_KEY.
Is Helionyx maintained?
The last commit was 28 days ago (2026-10-07). The latest release is v0.3.0.
How does Helionyx compare with other MCP servers?
safety score 83/100 (higher than 65% of 48,255 servers); tools 22 (the typical server has 7); tools that change things 36% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.