# io.github.cogswellspacely8-star/simengine (pypi · simengine-mcp)

Monte Carlo decision-intelligence over MCP: simulate, optimize, and decide under uncertainty.

- Trust score: 24/100 (low)
- Change this week: −23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- pypi · `simengine-mcp`: 24/100 (this document), [markdown](https://verifymcp.io/servers/cogswellspacely8-star-simengine/simengine-mcp.md), [page](https://verifymcp.io/servers/cogswellspacely8-star-simengine/simengine-mcp)

## Channel facts

- Registry: `pypi`
- Package: `simengine-mcp`
- Version: `3.0.1`
- 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**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 45/100
  - 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 22 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 0/100
  - Schema quality not yet verified: our sandbox run of this package did not complete, so we have no schema to assess.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: our sandbox run of this package did not complete, so we have no schema to compare.
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: our sandbox run of this package did not complete, so we have no tool definitions to assess.
- **Capabilities**: 0/100
  - Protocol version not yet verified: our sandbox run of this package did not complete, so we never saw its MCP handshake.

**Unverified: 4 categories.** Categories scored 0 because our sandbox run of this package has not given us the schema these checks need to read. That is a gap on our side rather than a finding about the package, and we only credit what we can confirm, so the score stands at 0 until the capture succeeds. We are working through the fleet, so this normally clears without any action from you.

## Install

### Claude

```bash
claude mcp add cogswellspacely8-star-simengine -- uvx simengine-mcp
```

### Codex

```bash
codex mcp add cogswellspacely8-star-simengine -- uvx simengine-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cogswellspacely8-star-simengine": {
      "type": "local",
      "command": [
        "uvx",
        "simengine-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add cogswellspacely8-star-simengine --command uvx --arg simengine-mcp
```

### Hermes

```yaml
mcp_servers:
  cogswellspacely8-star-simengine:
    command: "uvx"
    args: ["simengine-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "cogswellspacely8-star-simengine": {
      "command": "uvx",
      "args": [
        "simengine-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.

### 2026-08-01 (score 24, −5)

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

### 2026-07-30 (score 29, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-28 (score 47, 0)

- [functional] Tool coverage: Tool coverage not yet verified: our sandbox run of this package did not complete, so we have no tool definitions to assess.
- [functional] Schema quality: Schema quality not yet verified: our sandbox run of this package did not complete, so we have no schema to assess.

### 2026-07-26 (score 47)

First indexed and scored.

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

## MCP tools (9)

### `simulate` (~146 tokens)

Run a Monte Carlo simulation. Provide either a domain filename (from the domains/ directory) or an inline config JSON. Returns statistics, safety results, fitness score, and a narrative summary.

Input parameters:

- `config` (object): Inline domain config JSON (alternative to domain filename)
- `domain` (string): Domain config filename (e.g. 'saas_startup.json')
- `n_simulations` (integer): Number of simulations to run (default: from config)
- `overrides` (object): Dot-path overrides applied to the config, e.g. {'parameters.close_rate.params.mode': 0.35}
- `seed` (integer): Random seed for reproducibility (default: 42)

### `list_domains` (~22 tokens)

List all available domain configuration files in the SimEngine domains/ directory.

### `validate_config` (~37 tokens)

Validate a domain configuration JSON. Returns whether it is valid and any errors found.

Input parameters:

- `config` (object, required): The domain config JSON to validate

### `optimize` (~70 tokens)

Run evolutionary optimization on a domain to find the best control settings. Uses a genetic algorithm with safety constraints.

Input parameters:

- `domain` (string, required): Domain config filename
- `generations` (integer): Number of GA generations (default: 15)
- `population` (integer): Population size per generation (default: 20)

### `update_bayesian` (~93 tokens)

Bayesian-update simulation parameters using real observed data. Uses conjugate prior updates (Beta-Binomial, Gamma-Poisson, Normal-Normal) to calibrate the model.

Input parameters:

- `domain` (string, required): Domain config filename
- `observations` (object, required): Map of variable_name to array of observed values, e.g. {'close_rate': [0.25, 0.30, 0.28]}

### `convergence_check` (~73 tokens)

Run convergence diagnostics to verify that the simulation sample size is sufficient. Tests whether statistics stabilize as N increases.

Input parameters:

- `domain` (string, required): Domain config filename
- `max_runs` (integer): Maximum runs to test (default: 10000)
- `metric` (string): Target metric to check (default: first metric)

### `sensitivity_analysis` (~97 tokens)

Run one-at-a-time sensitivity analysis to rank which input parameters drive the most output variance. Returns elasticity and relative importance scores.

Input parameters:

- `domain` (string, required): Domain config filename
- `metric` (string): Target metric to analyze (default: first metric)
- `n_base` (integer): Base simulation count (default: 1000)
- `n_perturb` (integer): Perturbation trials per parameter (default: 10)

### `baseline_comparison` (~63 tokens)

Compare Monte Carlo simulation results to a deterministic (spreadsheet-style) single-point forecast. Shows the risk information hidden by deterministic forecasting.

Input parameters:

- `domain` (string, required): Domain config filename
- `n_simulations` (integer): MC simulation count (default: 5000)

### `decide_under_uncertainty` (~245 tokens)

Decision gate for agents. Runs a Monte Carlo simulation and returns whether to PROCEED or ESCALATE based on how much of the OUTCOME distribution falls inside an acceptable range you specify. Returns the full outcome distribution plus a proceed/escalate flag and a plain-English reason. Use this to stop a multi-step agent from acting on an overconfident point estimate. NOTE: this models OUTCOME RISK (the spread of results given uncertain inputs) — not the language model's own token confidence.

Input parameters:

- `acceptable` (object, required): Acceptable range for the metric; provide at least one of 'min' or 'max'.
- `config` (object): Inline domain config JSON (alternative to domain filename)
- `domain` (string): Domain config filename (alternative to config)
- `metric` (string, required): The output metric to evaluate the decision against
- `min_confidence` (number): Probability mass that must fall within the acceptable range to proceed (default: 0.8)
- `n_simulations` (integer): Number of simulations to run (default: from config)
- `seed` (integer): Random seed for reproducibility (default: 42)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/cogswellspacely8-star-simengine/simengine-mcp#diagnostics

## Score history

- 2026-08-03: 24
- 2026-08-02: 24
- 2026-08-01: 24
- 2026-07-30: 29
- 2026-07-29: 47
- 2026-07-28: 47
- 2026-07-27: 47
- 2026-07-26: 47

## Links

- PyPI project: https://pypi.org/project/simengine-mcp/
- Socket report: https://socket.dev/pypi/package/simengine-mcp
- Repository: https://github.com/cogswellspacely8-star/simengine
- Changelog RSS feed: https://verifymcp.io/servers/cogswellspacely8-star-simengine/simengine-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/cogswellspacely8-star-simengine/simengine-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/cogswellspacely8-star-simengine/simengine-mcp