# Helionyx (pypi · helionyx)

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

- Trust score: 47/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `helionyx`: 47/100 (this document), [markdown](https://verifymcp.io/servers/jayzilva-helionyx/helionyx.md), [page](https://verifymcp.io/servers/jayzilva-helionyx/helionyx)

## Channel facts

- Registry: `pypi`
- Package: `helionyx`
- Version: `0.3.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 49/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 6 of 58 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 28 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 36/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1777 tokens (~77/item across 23 items; 22 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 78/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 24% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 22 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 24 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Helionyx MCP server?

Helionyx runs locally as a PyPI package, launched with uvx helionyx. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add jayzilva-helionyx -- uvx helionyx
```

### Cursor

```json
{
  "mcpServers": {
    "jayzilva-helionyx": {
      "command": "uvx",
      "args": [
        "helionyx"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "jayzilva-helionyx": {
      "command": "uvx",
      "args": [
        "helionyx"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add jayzilva-helionyx -- uvx helionyx
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jayzilva-helionyx": {
      "type": "local",
      "command": [
        "uvx",
        "helionyx"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add jayzilva-helionyx --command uvx --arg helionyx
```

### Hermes

```yaml
mcp_servers:
  jayzilva-helionyx:
    command: "uvx"
    args: ["helionyx"]
```

### Netclaw

```json
{
  "McpServers": {
    "jayzilva-helionyx": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "helionyx"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add jayzilva-helionyx -t stdio -c uvx -a helionyx
```

### Other

```json
{
  "mcpServers": {
    "jayzilva-helionyx": {
      "command": "uvx",
      "args": [
        "helionyx"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 47, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-30 (score 62, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-17 (score 47, +23)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → 0
- [functional] First check of Tool coverage: 24
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fair
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100

### 2026-10-14 (score 24, −15)

- [security regression] Malware scan: pass → unverified
- [security] Stability: Stability not yet verified: this package could not be installed in a clean environment, so we have no schema to compare.
- [security] Tool safety: Tool safety not yet verified: this package could not be installed in a clean environment, so we have no tool text to scan.
- [functional] Schema quality: Schema quality not yet verified: this package could not be installed in a clean environment, so we have no schema to assess.
- [functional] Capabilities: Protocol version not yet verified: this package could not be installed in a clean environment, so we never saw its MCP handshake.
- [functional] Tool coverage: Tool coverage not yet verified: this package could not be installed in a clean environment, so we have no tool definitions to assess.

### 2026-10-13 (score 39, +18)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: partial → pass
- [functional] Dependency health: partial → 0.96

### 2026-10-12 (score 21, −3)

- [security regression] Known CVEs: pass → partial
- [functional] Dependency health: 0.96 → partial

### 2026-10-08 (score 24)

First indexed and scored.

## MCP tools (22)

### `create_site` (~83 tokens)

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

Input parameters:

- `country_pack` (string)
- `elevation_m`
- `latitude` (number, required): WGS84 decimal degrees
- `longitude` (number, required): WGS84 decimal degrees
- `name` (string, required)
- `timezone`: IANA zone; default from the country pack

Output parameters:

- `country_pack` (string)
- `elevation_m`
- `latitude` (number)
- `longitude` (number)
- `name` (string)
- `site_id` (string)
- `timezone` (string)

### `fetch_resource` (~75 tokens)

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.

Input parameters:

- `fill_long_gaps` (boolean)
- `site_id` (string, required)
- `source` (string)
- `year` (integer)

Output parameters:

- `content_hash` (string)
- `dataset_id` (string)
- `kind` (string)
- `provenance` (object)
- `quality_flags` (array)
- `resource_uri` (string)
- `site_id` (string)
- `source` (string)
- `stats` (object)
- `synthetic` (boolean)

### `import_timeseries` (~164 tokens)

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.

Input parameters:

- `base_resource_id`: Resource dataset to copy other variables from
- `csv_text`: CSV content; header encodes the unit, e.g. load_kw
- `extend_partial` (boolean): Load only: extend 4+ weeks of timestamped data to a full year (partly synthetic)
- `file_path`: Path inside the Helionyx workspace
- `height_m`: Anemometer height for wind data
- `kind` (string, required)
- `monthly_kwh`
- `resolution_min` (integer)
- `site_id` (string, required)

Output parameters:

- `content_hash` (string)
- `dataset_id` (string)
- `kind` (string)
- `provenance` (object)
- `quality_flags` (array)
- `resource_uri` (string)
- `site_id` (string)
- `source` (string)
- `stats` (object)
- `synthetic` (boolean)

### `synthesize_load` (~112 tokens)

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

Input parameters:

- `components` (array, required): Archetypes with a count, annual_kwh or peak_kw, e.g. [{archetype: 'hotel', count: 60}]
- `monthly_kwh`: 12 monthly kWh values (January–December), e.g. from bills, to calibrate the profile
- `seed` (integer)
- `site_id` (string, required)
- `variability`

Output parameters:

- `content_hash` (string)
- `dataset_id` (string)
- `kind` (string)
- `provenance` (object)
- `quality_flags` (array)
- `resource_uri` (string)
- `site_id` (string)
- `source` (string)
- `stats` (object)
- `synthetic` (boolean)

### `list_tariffs` (~48 tokens)

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

Input parameters:

- `as_of`
- `category`
- `country_pack` (string)
- `utility`

Output parameters:

- `count` (integer)
- `pack` (string)
- `tariffs` (array)

### `get_tariff` (~77 tokens)

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

Input parameters:

- `as_of`
- `country_pack` (string)
- `tariff_id` (string, required): Revision ID (lk.ceb.H2@2025-01-01) or category ID (lk.ceb.H2)

Output parameters:

- `pack` (string)
- `period_names` (array)
- `tariff` (object)
- `warnings` (array)

### `compute_bill` (~78 tokens)

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

Input parameters:

- `country_pack` (string)
- `demand_peak_factor` (number)
- `export_id`
- `export_scheme` (string)
- `import_id`
- `load_id`
- `tariff_id` (string, required)

Output parameters:

- `annual_total` (number)
- `currency` (string)
- `export_scheme` (string)
- `months` (array)
- `tariff_id` (string)
- `warnings` (array)

### `list_components` (~43 tokens)

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

Input parameters:

- `country_pack` (string)
- `query`
- `type`

Output parameters:

- `components` (array)
- `count` (integer)
- `pack` (string)

### `create_scenario` (~64 tokens)

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.

Input parameters:

- `parent_scenario_id`: Create a new version of this scenario
- `scenario` (required)

Output parameters:

- `candidate_count` (integer)
- `error_count` (integer)
- `resource_uri` (string)
- `scenario_hash` (string)
- `scenario_id` (string)
- `version` (integer)
- `warning_count` (integer)

### `validate_scenario` (~50 tokens)

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.

Input parameters:

- `scenario_id` (string, required)

Output parameters:

- `assumptions` (array)
- `candidate_count` (integer)
- `errors` (array)
- `scenario_hash` (string)
- `scenario_id` (string)
- `valid` (boolean)
- `warnings` (array)

### `run_optimization` (~141 tokens)

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.

Input parameters:

- `keep_timeseries_top_n`
- `max_evaluations` (integer): Heuristic budget
- `scenario_id` (string, required)
- `solver` (string): native = full enumeration; heuristic = seeded pattern search for large spaces; reopt / microgridspy / sama = external cross-check solvers
- `sort_by` (string)
- `wait_seconds` (number): 0 returns immediately; up to 20 waits and streams progress notifications

Output parameters:

- `batch_id`
- `eta_s`
- `job_id` (string)
- `progress_pct`
- `run_id`
- `state` (string)

### `get_job_status` (~50 tokens)

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

Input parameters:

- `job_id` (string, required)
- `wait_seconds` (number)

Output parameters:

- `batch_id`
- `eta_s`
- `job_id` (string)
- `progress_pct`
- `run_id`
- `state` (string)

### `cancel_job` (~23 tokens)

Cancel a queued or running job.

Input parameters:

- `job_id` (string, required)

Output parameters:

- `batch_id`
- `eta_s`
- `job_id` (string)
- `progress_pct`
- `run_id`
- `state` (string)

### `get_results` (~89 tokens)

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.

Input parameters:

- `filters`: Bounds on sizes or metrics, e.g. {"bess_kwh": {"max": 200}}
- `run_id` (string, required)
- `sort_by`
- `top_n` (integer)

Output parameters:

- `base_case`
- `candidates` (array)
- `currency` (string)
- `disclaimer` (string)
- `feasible_count` (integer)
- `infeasible_count` (integer)
- `provenance` (object)
- `run_id` (string)
- `scenario_hash` (string)
- `sorted_by` (string)

### `get_pareto_front` (~64 tokens)

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.

Input parameters:

- `max_points` (integer)
- `run_id` (string, required)

Output parameters:

- `disclaimer` (string)
- `front_size` (integer)
- `objectives` (array)
- `points` (array)
- `run_id` (string)

### `explain_run` (~72 tokens)

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.

Input parameters:

- `compare_to` (string)
- `rank` (integer): 0 = base case
- `run_id` (string, required)

Output parameters:

- `binding_constraints` (array)
- `currency` (string)
- `disclaimer` (string)
- `dispatch_statistics` (object)
- `npc` (number)
- `npc_by_cost_type` (object)
- `provenance` (object)
- `rank` (integer)
- `run_id` (string)
- `sentences` (array)
- `top_cost_drivers` (array)
- `uncertain_inputs` (array)

### `get_monthly_summary` (~43 tokens)

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

Input parameters:

- `rank` (integer)
- `run_id` (string, required)

Output parameters:

- `annual_totals` (object)
- `currency` (string)
- `disclaimer` (string)
- `months` (array)
- `rank` (integer)
- `run_id` (string)

### `run_sensitivity` (~128 tokens)

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.

Input parameters:

- `scenario_id` (string, required)
- `solver` (string)
- `variables` (array, required): One variable (sweep) or two (grid): dotted scenario path and values, e.g. {path: 'components.bess.overrides.capital_per_unit', values: [60000, 80000, 100000]}
- `wait_seconds` (number)

Output parameters:

- `batch_id`
- `eta_s`
- `job_id` (string)
- `progress_pct`
- `run_id`
- `state` (string)

### `get_sensitivity_results` (~33 tokens)

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

Input parameters:

- `batch_id` (string, required)

Output parameters:

- `batch_id` (string)
- `cases` (array)
- `disclaimer` (string)
- `elasticities` (array)
- `variable` (string)

### `compare_runs` (~45 tokens)

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

Input parameters:

- `rank` (integer)
- `run_ids` (array, required)

Output parameters:

- `disclaimer` (string)
- `rank` (integer)
- `reference_run_id` (string)
- `runs` (array)

### `export_homer_csv` (~42 tokens)

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

Input parameters:

- `run_id`
- `scenario_id`

Output parameters:

- `files`
- `path`
- `resource_uri`

### `export_report` (~52 tokens)

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

Input parameters:

- `format` (string)
- `run_id` (string, required)

Output parameters:

- `files`
- `path`
- `resource_uri`

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/jayzilva-helionyx/helionyx#diagnostics

## Score history

- 2026-11-05: 47
- 2026-11-04: 62
- 2026-11-03: 62
- 2026-11-02: 62
- 2026-11-01: 62
- 2026-10-31: 62
- 2026-10-30: 62
- 2026-10-29: 47
- 2026-10-28: 47
- 2026-10-27: 47
- 2026-10-26: 47
- 2026-10-25: 47
- 2026-10-24: 47
- 2026-10-23: 47
- 2026-10-22: 47
- 2026-10-21: 47
- 2026-10-20: 47
- 2026-10-19: 47
- 2026-10-18: 47
- 2026-10-17: 47
- 2026-10-16: 24
- 2026-10-15: 24
- 2026-10-14: 24
- 2026-10-13: 39
- 2026-10-12: 21
- 2026-10-08: 24

## Common questions

### What is the Helionyx MCP server?

Helionyx is an MCP server listed in the public MCP registry as io.github.Jayzilva/helionyx. Size hybrid solar PV, wind, battery, diesel and grid systems: hourly simulation, NPC ranking. This page covers its PyPI package (helionyx).

### Is the Helionyx MCP server safe to use?

Helionyx scores 47 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Helionyx MCP server expose?

Helionyx exposes 22 tools: create_site, fetch_resource, import_timeseries, synthesize_load, list_tariffs, and 17 more. Their descriptions and schemas cost roughly 1,576 tokens of context every time the server is loaded.

### Is the Helionyx MCP server still maintained?

Helionyx is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Helionyx MCP server under?

Helionyx declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/helionyx/
- Socket report: https://socket.dev/pypi/package/helionyx
- Repository: https://github.com/Jayzilva/helionyx
- Changelog RSS feed: https://verifymcp.io/servers/jayzilva-helionyx/helionyx.xml
- Changelog JSON feed: https://verifymcp.io/servers/jayzilva-helionyx/helionyx.json
- HTML version of this page: https://verifymcp.io/servers/jayzilva-helionyx/helionyx