# io.github.meszarosjan/steel-metallurgy-material-simulator-mcp (npm · material-simulator-mcp)

No-key MCP server for steel equilibrium, TTT/CCT kinetics, phase-boundary and measured-data tools.

- Trust score: 62/100 (medium)
- Change this week: +44
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `material-simulator-mcp`: 62/100 (this document), [markdown](https://verifymcp.io/servers/meszarosjan-steel-metallurgy-material-simulator-mcp/material-simulator-mcp.md), [page](https://verifymcp.io/servers/meszarosjan-steel-metallurgy-material-simulator-mcp/material-simulator-mcp)

## Channel facts

- Registry: `npm`
- Package: `material-simulator-mcp`
- Version: `0.1.4`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 26 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1143 tokens (~127/item across 9 items; 6 tools + 3 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add meszarosjan-steel-metallurgy-material-simulator- -- npx -y material-simulator-mcp
```

### Codex

```bash
codex mcp add meszarosjan-steel-metallurgy-material-simulator- -- npx -y material-simulator-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "meszarosjan-steel-metallurgy-material-simulator-": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "material-simulator-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add meszarosjan-steel-metallurgy-material-simulator- --command npx --arg -y --arg material-simulator-mcp
```

### Hermes

```yaml
mcp_servers:
  meszarosjan-steel-metallurgy-material-simulator-:
    command: "npx"
    args: ["-y", "material-simulator-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "meszarosjan-steel-metallurgy-material-simulator-": {
      "command": "npx",
      "args": [
        "-y",
        "material-simulator-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-03 (score 62, +4)

- [functional improvement] Stability: unverified → 0.23

### 2026-08-02 (score 58, +58)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → excellent
- [functional] Licence: MIT

### 2026-08-01 (score 0, −23)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 23, +5)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-30 (score 18, −23)

- [functional regression] Schema quality: 100 → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-28 (score 41, +23)

- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100
- [functional] First check of Schema quality: unverified
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 0

### 2026-07-27 (score 18)

First indexed and scored.

## MCP tools (6)

### `interpret_steel_state` (~210 tokens)

Interpret steel state

Interpret the equilibrium state of plain-carbon steel at a given carbon
content and temperature: stable phases, microstructure constituents
(pearlite, proeutectoid ferrite or cementite), lever-rule phase mass
fractions, qualitative mechanical property tendencies and typical
applications. Use for questions like "what phases does 0.45% carbon
steel have at 700 C", "what is the microstructure of slowly cooled
eutectoid steel", or "why is high-carbon steel brittle". Educational
equilibrium model (Fe-Fe3C, 0-2.14 wt% C, 20-1147 C) with explicit
assumptions, refusal boundaries and verification needs in every
response. Does NOT predict quenching or cooling-rate effects — use
interpret_continuous_cooling or interpret_isothermal_hold for that.

Input parameters:

- `carbon_wt_percent` (number, required)
- `lang` (string)
- `temperature_c` (number, required)

### `interpret_continuous_cooling` (~232 tokens)

Interpret continuous cooling

Interpret what forms when eutectoid plain-carbon steel (~0.76 wt% C) is
cooled at a constant rate to room temperature: fractions of pearlite,
bainite, martensite and retained austenite, via Scheil additivity over
a published TTT dataset and Koistinen-Marburger martensite kinetics.
Accepts an explicit cooling rate (0.005-2000 C/s) or a named quench
preset: furnace, air, oil, or water. Use for questions like "what
happens if I quench eutectoid steel in oil", "how fast must steel cool
to become fully martensitic", or "will air cooling give pearlite".
Educational tier, eutectoid composition only; every response carries
the assumed process history, assumptions, refusals (including
section-size effects and other compositions) and verification needs.

Input parameters:

- `austenitizing_c` (number)
- `cooling_rate_c_per_s` (number)
- `lang` (string)
- `preset` (string)

### `interpret_isothermal_hold` (~190 tokens)

Interpret isothermal hold

Interpret an isothermal hold (TTT / austempering-style treatment) of
eutectoid plain-carbon steel: quench to a hold temperature, hold for a
given time, then quench to room temperature. Returns transformation
start/finish times at that temperature, the JMAK transformed fraction,
and product fractions (coarse/fine pearlite, upper/lower bainite,
martensite, retained austenite) at the hold and after final quench.
Use for questions like "what forms if steel is held at 350 C for 100
seconds" or "how long until transformation finishes at 600 C".
Educational tier, eutectoid composition only, with explicit process
history, assumptions, refusals and verification needs.

Input parameters:

- `hold_temperature_c` (number, required)
- `hold_time_s` (number, required)
- `lang` (string)

### `get_phase_boundaries` (~159 tokens)

Get phase boundaries

Get the A1, A3 and Acm transformation temperatures of the Fe-Fe3C
phase diagram for a given carbon content, with the sourced curve model
shown (Andrews 1965 sqrt-of-carbon A3 shape normalized to the diagram's
fixed points; Acm interpolated over published anchor points — sources
and anchor tables included in the response, not a black box). Use for
questions like "at what temperature does 0.3% carbon steel become fully
austenitic" or "what is the A3 temperature of C45". Omit the carbon
parameter to get the fixed points (G, S, E) and full curve model.

Input parameters:

- `carbon_wt_percent` (number)

### `lookup_measured_steel_data` (~203 tokens)

Lookup measured steel data

Look up MEASURED (not modeled) steel datasets transcribed from
published sources, each with full citation, license, ready-made
attribution string and extraction provenance down to the table or
figure of origin. Covers dilatometric CCT hardness data for named
steel heats, continuous-cooling phase fractions, isothermal/parametric
cooling kinetics, and historical digitized TTT data (including the
founding 1930 Davenport & Bain eutectoid dataset) — sources are CC-BY
or public domain. Use when the user needs real measured hardness or
transformation values with a citable source rather than a model
estimate — e.g. "what measured hardness does S960MC reach at 30 C/s".
Call without arguments for the current list of available datasets
(the list grows over time); pass dataset_id for full records.

Input parameters:

- `dataset_id` (string)
- `lang` (string)

### `get_steel_glossary` (~92 tokens)

Get steel glossary

Get a structured glossary of steel phases, microstructure constituents
and related terms (ferrite, austenite, cementite, pearlite, bainite,
martensite and more), each explained at three levels: simple,
technical and scientific. English, Slovak and Czech. Use when explaining
metallurgy concepts at an audience-appropriate depth.

Input parameters:

- `lang` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/meszarosjan-steel-metallurgy-material-simulator-mcp/material-simulator-mcp#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 58
- 2026-08-01: 0
- 2026-07-31: 23
- 2026-07-30: 18
- 2026-07-28: 41
- 2026-07-27: 18

## Links

- npm package: https://www.npmjs.com/package/material-simulator-mcp
- Socket report: https://socket.dev/npm/package/material-simulator-mcp
- Changelog RSS feed: https://verifymcp.io/servers/meszarosjan-steel-metallurgy-material-simulator-mcp/material-simulator-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/meszarosjan-steel-metallurgy-material-simulator-mcp/material-simulator-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/meszarosjan-steel-metallurgy-material-simulator-mcp/material-simulator-mcp