# io.github.inity13/agentstack-mcp (npm · agentstack-mcp)

Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.

- Trust score: 65/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-20

## Components

- remote · `agentstack-mcp.pages.dev`: 63/100, [markdown](https://verifymcp.io/servers/inity13-agentstack-mcp/agentstack-mcp.md), [page](https://verifymcp.io/servers/inity13-agentstack-mcp/agentstack-mcp)
- npm · `agentstack-mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/inity13-agentstack-mcp/agentstack-mcp-2.md), [page](https://verifymcp.io/servers/inity13-agentstack-mcp/agentstack-mcp-2)

## Channel facts

- Registry: `npm`
- Package: `agentstack-mcp`
- Version: `1.0.1`
- 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 2026-08-20.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 1 dependencies flagged as unhealthy.
- **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 (MIT).
  - Actively maintained (last published 7 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 51/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1344 tokens (~56/item across 24 items; 24 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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 inity13-agentstack-mcp -- npx -y agentstack-mcp
```

### Codex

```bash
codex mcp add inity13-agentstack-mcp -- npx -y agentstack-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "inity13-agentstack-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "agentstack-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add inity13-agentstack-mcp --command npx --arg -y --arg agentstack-mcp
```

### Hermes

```yaml
mcp_servers:
  inity13-agentstack-mcp:
    command: "npx"
    args: ["-y", "agentstack-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "inity13-agentstack-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "agentstack-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.

### 2026-08-20 (score 65, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-12 (score 61)

First indexed and scored.

## MCP tools (24)

### `list_capabilities` (~28 tokens)

Discovery: namespaces (sim_*, decide_*, calc_*), composite tools, and profiles.

### `health_check` (~16 tokens)

Aggregated health for the whole stack.

### `sim_run` (~65 tokens)

SIMULATE. Deterministic what-if projection from a template or free-form 'metrics' model.

Input parameters:

- `horizon` (integer)
- `inputs` (object)
- `metrics` (array)
- `period_label` (string)
- `template` (string)

### `sim_sensitivity` (~90 tokens)

SIMULATE. Vary scenario inputs and show impact on a target metric.

Input parameters:

- `horizon` (integer)
- `inputs` (object)
- `period_label` (string)
- `steps` (integer)
- `target_metric` (string)
- `template` (string, required)
- `variable` (string)
- `variables` (array)
- `variation` (number)

### `sim_break_even` (~86 tokens)

SIMULATE. Solve for the input value that makes a metric hit a target.

Input parameters:

- `bounds` (array)
- `horizon` (integer)
- `inputs` (object)
- `period_label` (string)
- `solve_for` (string, required)
- `target_metric` (string)
- `target_value` (number, required)
- `template` (string, required)

### `sim_compare` (~51 tokens)

SIMULATE. Compare 2-3 scenarios side by side.

Input parameters:

- `compare_metric` (string)
- `goal` (string)
- `horizon` (integer)
- `scenarios` (array, required)

### `sim_list_templates` (~22 tokens)

SIMULATE. List every scenario template with inputs and outputs.

### `decide` (~54 tokens)

DECIDE. Rank options against weighted criteria; returns winner, ranking, breakdowns, explanation.

Input parameters:

- `criteria` (array, required)
- `method` (string)
- `options` (array, required)
- `scores` (object, required)

### `decide_score` (~46 tokens)

DECIDE. Full normalized scored matrix + ranking.

Input parameters:

- `criteria` (array, required)
- `method` (string)
- `options` (array, required)
- `scores` (object, required)

### `decide_sensitivity` (~68 tokens)

DECIDE. Robustness of the winner to CRITERIA-WEIGHT changes.

Input parameters:

- `criteria` (array, required)
- `method` (string)
- `options` (array, required)
- `scores` (object, required)
- `steps` (integer)
- `variation` (number)

### `decide_compare_two` (~64 tokens)

DECIDE. Head-to-head between exactly two options.

Input parameters:

- `criteria` (array, required)
- `method` (string)
- `option_a` (string)
- `option_b` (string)
- `options` (array)
- `scores` (object, required)

### `decide_list_methods` (~16 tokens)

DECIDE. List scoring methods.

### `calc_metric` (~56 tokens)

COMPUTE. Exact business/SaaS/finance metric (ltv, cac, rule_of_40, nrr, ...).

Input parameters:

- `currency` (string)
- `metric` (string, required)
- `params` (object, required)

### `calc_list_metrics` (~18 tokens)

COMPUTE. List supported metrics + schemas.

### `calc_currency_convert` (~55 tokens)

COMPUTE. Convert currencies with Decimal precision.

Input parameters:

- `amount` (number, required)
- `date` (string)
- `from_currency` (string, required)
- `live` (boolean)
- `to_currency` (string, required)

### `calc_business_days` (~64 tokens)

COMPUTE. Business-day arithmetic with holidays.

Input parameters:

- `custom_holidays` (array)
- `days` (integer)
- `end_date` (string)
- `operation` (string, required)
- `region` (string)
- `start_date` (string, required)

### `calc_compound_growth` (~90 tokens)

COMPUTE. future_value | present_value | cagr.

Input parameters:

- `begin_value` (number)
- `compounding` (string)
- `currency` (string)
- `end_value` (number)
- `future_value` (number)
- `operation` (string, required)
- `present_value` (number)
- `rate` (number)
- `years` (number)

### `calc_npv` (~38 tokens)

COMPUTE. Net Present Value.

Input parameters:

- `cashflows` (array, required)
- `currency` (string)
- `rate` (number, required)

### `calc_irr` (~32 tokens)

COMPUTE. Internal Rate of Return.

Input parameters:

- `cashflows` (array, required)
- `guess` (number)

### `calc_loan_amortization` (~67 tokens)

COMPUTE. Level-payment loan schedule.

Input parameters:

- `annual_rate` (number, required)
- `currency` (string)
- `extra_payment` (number)
- `include_schedule` (boolean)
- `principal` (number, required)
- `term_months` (integer, required)

### `calc_depreciation` (~58 tokens)

COMPUTE. Depreciation schedule.

Input parameters:

- `cost` (number, required)
- `currency` (string)
- `method` (string, required)
- `salvage_value` (number, required)
- `useful_life_years` (integer, required)

### `plan_to_valuation` (~96 tokens)

COMPOSITE (simulate -> compute). Project a scenario, value its cash-flow line (NPV/IRR).

Input parameters:

- `cashflow_metric` (string, required)
- `currency` (string)
- `horizon` (integer)
- `initial_investment` (number)
- `inputs` (object)
- `period_label` (string)
- `rate` (number, required)
- `template` (string, required)

### `evaluate_options_with_scenarios` (~78 tokens)

COMPOSITE (simulate -> decide). Project each option, rank the outcomes.

Input parameters:

- `criteria` (array, required)
- `horizon` (integer)
- `inputs` (object)
- `method` (string)
- `options` (array, required)
- `period_label` (string)
- `template` (string)

### `stress_test_decision` (~86 tokens)

COMPOSITE (simulate x decide). Stress a scenario assumption and see if the winner holds.

Input parameters:

- `criteria` (array, required)
- `horizon` (integer)
- `inputs` (object)
- `method` (string)
- `options` (array, required)
- `period_label` (string)
- `stress` (object, required)
- `template` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/inity13-agentstack-mcp/agentstack-mcp-2#diagnostics

## Score history

- 2026-08-20: 65
- 2026-08-19: 61
- 2026-08-18: 61
- 2026-08-17: 61
- 2026-08-16: 61
- 2026-08-15: 61
- 2026-08-14: 61
- 2026-08-13: 61
- 2026-08-12: 61

## Links

- npm package: https://www.npmjs.com/package/agentstack-mcp
- Socket report: https://socket.dev/npm/package/agentstack-mcp
- Repository: https://github.com/inity13/agentstack-mcp
- Changelog RSS feed: https://verifymcp.io/servers/inity13-agentstack-mcp/agentstack-mcp-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/inity13-agentstack-mcp/agentstack-mcp-2.json
- HTML version of this page: https://verifymcp.io/servers/inity13-agentstack-mcp/agentstack-mcp-2