# `io.github.inity13/scenariosim-mcp` on anlyon.dev

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://anlyon.dev/servers/io.github.inity13/scenariosim-mcp
- JSON: https://anlyon.dev/api/v1/servers/io.github.inity13/scenariosim-mcp
- Version: 1.0.2 (active)
- Publisher: io.github.inity13 (GitHub account)
- Runs: remote (streamable-http), local (npm)
- Sign-in to list tools: none
- Repository: https://github.com/inity13/scenariosim-mcp
- Metadata from the official MCP Registry, synced 2026-10-21T18:36:23.724Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Deterministic what-if & scenario simulation for AI agents: projections, sensitivity & break-even.
```

Scanned 2026-10-21T19:23:41.180Z over streamable-http.

**6 tools: 5 change things and 1 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 5 | ask |
| Only reads | read | 1 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | none |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | none |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

No check matched anything in these tool definitions.


## Changes things (5)

Creates or changes something that can be changed back. Claude Code: ask.

### `break_even`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Solve for the input value required to make an output metric hit a target value (deterministic bisection root-finding). Provide 'template', 'solve_for' (the input to solve), 'target_metric' (defaults to the primary output), and 'target_value'. Optionally pass 'bounds' [low, high] to constrain the search. Returns the required input value, the change from baseline, the achieved metric, and the residual. Assumes the metric is monotonic in the solved input over the range.
```

### `compare_scenarios`

- The name "compare_scenarios" says "compare": a word for reading.
- The description's first verb is "run": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Run 2-3 scenarios and compare their key_results side by side, with deltas against the first (baseline) scenario. Provide a 'scenarios' array where each entry is {name?, template, inputs} (each may set its own horizon, or pass a shared top-level 'horizon'). Optionally rank on 'compare_metric' with 'goal' ('max' default | 'min') to pick a winner, and set include_projections:true to also return per-period series.
```

### `health_check`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Server health, version, and capabilities (tools, templates, period labels, max horizon). No parameters.
```

### `run_scenario`

- The name "run_scenario" says "run": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Main simulation tool. Run a deterministic what-if projection from a pre-built template (saas_growth, pricing_change, churn_impact, cost_reduction, hiring_plan, cash_runway, unit_economics, marketing_funnel, compound_growth) OR a free-form 'metrics' model. Returns period-by-period projections, headline key_results, the exact assumptions used (with defaults filled in), the methodology, notes, and a plain-language explanation. Pass 'template' + 'inputs' (assumptions), plus optional 'horizon' and 'period_label'. 100% deterministic (40-digit decimal math).
```

### `sensitivity_analysis`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Vary one or more input assumptions and show the impact on a target output metric (one-at-a-time sensitivity). Provide 'template', the input to sweep via 'variable' (or 'variables' array), and 'target_metric' (defaults to the template's primary output). Control the sweep with 'variation' (fractional +/- around the baseline, default 0.2), 'steps' (default 5), or explicit 'values' / 'min'+'max'. Returns per-variable sweeps, an elasticity estimate, the output range, and a ranking of the most influential inputs.
```

## Only reads (1)

Looks things up and changes nothing. Claude Code: allow.

### `list_templates`

- The name "list_templates" says "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Discovery tool: list every pre-built scenario template (id, label, category, description, primary output, documented inputs with defaults/units, and available output metrics), plus how to run a custom free-form scenario and the supported period labels. No required parameters.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `scenariosim`:

```json
{
  "permissions": {
    "allow": [
      "mcp__scenariosim__list_templates"
    ],
    "ask": [
      "mcp__scenariosim__run_scenario",
      "mcp__scenariosim__sensitivity_analysis",
      "mcp__scenariosim__break_even",
      "mcp__scenariosim__compare_scenarios",
      "mcp__scenariosim__health_check"
    ],
    "deny": []
  }
}
```

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-10-22T15:00:26.846Z, unchanged since 2026-10-22T15:00:26.846Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://anlyon.dev/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| Reachable | `yes` |
| HTTP status of an anonymous initialize | `200` |
| tools/list served without credentials | `yes` |
| Tools that change things, listed without credentials | `5` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |

- **warn** Tools that change things, listed to anyone ([unauth-remote-writes](https://anlyon.dev/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.

https://scenariosim-mcp.pages.dev/mcp: tools/list returned 6 tools to an anonymous client, including run_scenario (write), sensitivity_analysis (write), break_even (write), compare_scenarios (write), health_check (write)
```