# io.github.26048608982lp-ai/gamenumerics (npm · mcp-server-gamenumerics)

Game numerical design & balance auditing MCP server — 17 deterministic tools, zero LLM guessing.

- Trust score: 69/100 (medium)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `mcp-server-gamenumerics`: 69/100 (this document), [markdown](https://verifymcp.io/servers/26048608982lp-ai-gamenumerics/mcp-server-gamenumerics.md), [page](https://verifymcp.io/servers/26048608982lp-ai-gamenumerics/mcp-server-gamenumerics)

## Channel facts

- Registry: `npm`
- Package: `mcp-server-gamenumerics`
- Version: `0.1.2`
- 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 2026-09-20.

- **Supply Chain Security**: 92/100
  - No malware found by supply-chain analysis.
  - Known CVEs were checked across the 3 of 4 dependencies we could resolve, so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Dependency health was assessed across the 3 of 4 dependencies we could resolve, so this covers what we could see, not the whole tree.
- **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 4 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2726 tokens (~160/item across 17 items; 17 tools + 0 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**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "eval_formula" implies "eval" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 17 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).

## Install

### How do I install the io.github.26048608982lp-ai/gamenumerics MCP server?

io.github.26048608982lp-ai/gamenumerics runs locally as an npm package, launched with npx -y mcp-server-gamenumerics. 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 26048608982lp-ai-gamenumerics -- npx -y mcp-server-gamenumerics
```

### Cursor

```json
{
  "mcpServers": {
    "26048608982lp-ai-gamenumerics": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-gamenumerics"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "26048608982lp-ai-gamenumerics": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-gamenumerics"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add 26048608982lp-ai-gamenumerics -- npx -y mcp-server-gamenumerics
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "26048608982lp-ai-gamenumerics": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mcp-server-gamenumerics"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add 26048608982lp-ai-gamenumerics --command npx --arg -y --arg mcp-server-gamenumerics
```

### Hermes

```yaml
mcp_servers:
  26048608982lp-ai-gamenumerics:
    command: "npx"
    args: ["-y", "mcp-server-gamenumerics"]
```

### Netclaw

```json
{
  "McpServers": {
    "26048608982lp-ai-gamenumerics": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "mcp-server-gamenumerics"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add 26048608982lp-ai-gamenumerics -t stdio -c npx -a -y mcp-server-gamenumerics
```

### Other

```json
{
  "mcpServers": {
    "26048608982lp-ai-gamenumerics": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-gamenumerics"
      ]
    }
  }
}
```

## 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.

### 2026-09-20 (score 69, +3)

- [functional improvement] Stability: unverified → 0.23

### 2026-09-14 (score 66, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-13 (score 51)

First indexed and scored.

## MCP tools (17)

### `list_tables` (~91 tokens)

列出当前工作区的全部数值表清单：表名、所属模块、行数、列名。回答数值问题前先用它定位要查哪张表、有哪些列可用。

Input parameters:

- `module` (string): 按模块过滤（可选）：settings/growth/equipment/level/hero/economy/rogue/talent/enemy/gamedata

### `read_table` (~158 tokens)

读取工作区内指定数值表的数据行。支持列选择、条件过滤（eq/ne/gt/gte/lt/lte/contains）、分页（offset/limit，默认前 20 行）。先用 list_tables 拿到表名和列名。

Input parameters:

- `columns` (array): 只返回指定列（可选）
- `filter` (array): 过滤条件，多条件 AND（可选）
- `limit` (number): 返回行数上限（默认 20，全表导出可设大）
- `offset` (number): 跳过前 N 行（默认 0）
- `table` (string, required): 表名，如 hero/成长表（来自 list_tables 的 table 字段）

### `battle_simulate` (~155 tokens)

战斗模拟：玩家面板 × 敌人面板的对拼计算（确定性引擎，非 LLM 估算）。返回击杀刀数、被击刀数、咬合比 killRatio、评级（easy/balanced/tight/impossible）、期望 DPS；可选 Monte Carlo 胜率。用于改数值后评估战斗咬合变化。

Input parameters:

- `enemy` (object, required): 敌人面板（来自 enemy/等级成长）
- `player` (object, required): 玩家面板（来自 hero/成长表 + 装备加成）
- `simulations` (number): Monte Carlo 局数（默认 0 不算胜率）

### `simulate_gacha` (~269 tokens)

概率模拟（确定性引擎）：mode=tiers 模拟无保底分层概率池（rogue 技能三选一、宝箱品质掉落）N 次抽取的各层次数分布与分位；mode=pity 模拟带保底的抽卡（基础概率+软/硬保底）抽数分布与期望。

Input parameters:

- `baseRate` (number): mode=pity：基础概率（如 0.006）
- `draws` (number): mode=tiers：单轮抽取次数（如一局 15 次三选一 = 15 抽）
- `hardPity` (number): mode=pity：硬保底抽数
- `iterations` (number): 模拟轮数（默认 1000）
- `mode` (string, required): tiers=分层池抽取；pity=保底抽卡
- `softPityIncrement` (number): mode=pity：软保底每抽概率增量
- `softPityStart` (number): mode=pity：软保底起始抽数
- `tiers` (array): mode=tiers 必填：各层名称与单次命中率（概率和须为 1）

### `compute_power` (~162 tokens)

战力计算（确定性引擎，EHP×EDPS 开方模型）：输入属性面板（中文键如 攻击/体力/暴击率/暴击伤害），返回战力、EDPS、EHP 与各属性边际价值。用于对比改数值前后的战力变化。

Input parameters:

- `attrs` (object, required): 属性面板，键可用中文（攻击/体力/暴击率/暴击伤害/攻速/防御）或英文
- `stdAtk` (number): 满级标准攻击锚（默认取面板攻击值）
- `stdSpeed` (number): 满级标准速度锚（默认 1，攻速倍率口径）

### `power_curve` (~281 tokens)

战力曲线（批量）：读成长表逐行（可采样）属性面板调 computePowerStats，一次产出「等级→战力」全曲线与形态摘要（首/中位/末档战力、成长倍率、形态判定：匀速/后期加速/台阶断点）。属性列自动按常用名识别（攻击/攻击力→attack、体力/生命→hp、防御→defense、攻速/速度→speed、暴击率→crit），识别不到时用 columns 显式指定。适合全曲线分析与成长×装备联合推导，替代多次单点 compute_power。

Input parameters:

- `columns` (object): 显式列映射 {attack:'属性.攻击', hp:'属性.体力', defense?, speed?, crit?}——自动识别失败或需换列时用
- `levelColumn` (string): 等级/序号列名，缺省取首列
- `sampleEvery` (number): 采样间隔（默认自动：行数>60 时取 ceil(行数/60)），首末行恒在采样内
- `table` (string, required): 成长表名（如 hero/成长表）

### `eval_formula` (~100 tokens)

确定性求值数值公式（四则/幂/括号/变量，支持中文变量名）。用于验证锚点公式、快速算数——数值永远由引擎算而非估算。

Input parameters:

- `expression` (string, required): 公式，如 100 * 1.08 ^ (等级 - 1)
- `variables` (object): 变量取值，如 {等级: 60}

### `audit_column` (~191 tokens)

列审计（对账）：用锚点公式重算指定列的每一行（变量 x=varColumn 该行值，i=行序），报告偏离公式超过阈值（默认 1%）的行——识别成长曲线的手调断点。先看 list_tables 的 columnPatterns 了解列的既有模式。

Input parameters:

- `column` (string, required): 被审计的数值列
- `expression` (string, required): 期望公式（x=varColumn 值，i=行序），如 100 + 5 * (x - 1)
- `table` (string, required): 目标表名
- `thresholdPct` (number): 偏离阈值百分比（默认 1）
- `varColumn` (string, required): 作为变量 x 的列（通常是等级/序号列）

### `infer_column_rule` (~186 tokens)

列规则推断（确定性拟合，逆向分析的起点）：对指定数值列拟合三大曲线族（等差/等比/幂律），返回最优规则——参数、吻合占比 fitPct、可直接使用的表达式——以及偏离规则的断点行（疑似手调）。分析成长/消耗曲线的构成规律先用它；得到规则后把 expression 交给 audit_column 复核，或用 write_table 的 apply_curve 按规则整列重算。

Input parameters:

- `column` (string, required): 要推断的数值列
- `table` (string, required): 目标表名（来自 list_tables）
- `thresholdPct` (number): 偏离阈值百分比（默认 1），超出即计为断点

### `infer_table_relation` (~241 tokens)

表内列间派生关系推断（确定性拟合）：判断「B 列 ≈ A 列 × k」的系数关系并标出偏离行（取整容限内免误报），或对整表数值列两两配对、自动发现基准锚点列与各列系数。还原「各装备属性 = 基准 × 装备系数」这类生成结构时用；发现系数后可与系数表（如 read_table 装备划分）对照确认同源性。列内时序规律（随行序怎么走）用 infer_column_rule，本工具管列与列的结构。

Input parameters:

- `columns` (array): 参与列。恰 2 列时输出该对的详细关系；多列为子集两两；缺省为全表数值列自动两两
- `table` (string, required): 目标表名（来自 list_tables）
- `thresholdPct` (number): 相对容差百分比（默认 1，与取整容限取大）

### `grade_workspace` (~128 tokens)

工作区分级（逆向接入第一步）：按输入契约三级分档扫描全部表——A 规范（双行表头点分列名比例/列生成模式命中率达标）、B 半规范（单行中文表头）、C 裸表（英文驼峰/无中文语义表头），输出工作区判级、逐表分级、覆盖率与孤儿表初判（无外键候选列且无角色候选信号）。分级结果可用 save_structure 固化到 structure.json。

### `profile_table` (~151 tokens)

单表画像（确定性统计，无 LLM）：行数、列类型分布、枚举度（distinct/行数）、单调性（递增/递减/无）、主键候选（唯一且非空列）、累计列校验（某列≈另一列逐行前缀和，取整容差）、角色候选（growth=有等级列且存在等差模式列；master_data=有索引/序号类列；cost=累计列校验成立）。逆向理解单表结构先用它，结论可经 save_structure 固化。

Input parameters:

- `table` (string, required): 目标表名（来自 list_tables）

### `infer_foreign_keys` (~201 tokens)

表间外键推断（值域包含检测，确定性）：from 列非空值域 ⊆ to 列值域、悬挂率 <5% 才成立，from 非空值 ≥3 防巧合；confidence = (1-悬挂率)×值域大小因子。输出候选关系边（kind=foreign_key，不落盘，供用户确认后经 save_structure 固化）。可指定 fromTable/toTable 定向检测；缺省全表两两扫描（输出按置信度排序的 topN 防爆炸）。

Input parameters:

- `fromTable` (string): 引用方表名（与 toTable 成对指定）
- `toTable` (string): 被引用方表名（与 fromTable 成对指定）
- `topN` (number): 全表扫描模式下输出候选数上限（默认 20，最大 50）

### `read_memory` (~41 tokens)

读取工作区全部项目记忆（项目画像 PROFILE.md + 事实流 facts.md）。回答与历史结论相关的问题前先查记忆。

### `list_workspaces` (~55 tokens)

列出全部可用工作区（位于本机工作区根，GND_WORKSPACES_DIR 环境变量控制，缺省 ~/.gamenumerics/workspaces）。切换工作区用 set_workspace。

### `set_workspace` (~52 tokens)

切换当前工作区（后续全部数值工具调用均作用于它）。name 须来自 list_workspaces 的列表。

Input parameters:

- `name` (string, required): 工作区名（来自 list_workspaces）

### `import_xlsx` (~264 tokens)

从本地 xlsx 文件（绝对路径）导入并创建工作区：读取工作簿全部 sheet（或 sheets 参数指定子集），双行表头自动合并为「父.子」复合列名，数值列自动识别等差/等比/常数模式，装配为规范化 tables/*.json + workspace.json 并设为当前工作区。headerRows 缺省由启发式探测（结果随摘要回显，探测失误可显式指定 1/2 重试）；同名工作区整体覆盖重建。导入后即可用 list_tables / read_table / audit_column 等工具审计数值。

Input parameters:

- `sheets` (array): 导入 sheet 子集与覆盖（可选；缺省导入全部 sheet，module=import，headerRows 自动探测）
- `workspaceName` (string): 工作区名（可选；缺省取文件名去扩展名。仅允许字母/数字与 -._，首字符须为字母/数字）
- `xlsxPath` (string, required): 本地 xlsx 文件绝对路径（Windows 正反斜杠均可，内部归一）

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/26048608982lp-ai-gamenumerics/mcp-server-gamenumerics#diagnostics

## Score history

- 2026-09-20: 69
- 2026-09-19: 66
- 2026-09-18: 66
- 2026-09-17: 66
- 2026-09-16: 66
- 2026-09-15: 66
- 2026-09-14: 66
- 2026-09-13: 51

## Common questions

### What is the io.github.26048608982lp-ai/gamenumerics MCP server?

io.github.26048608982lp-ai/gamenumerics is an MCP server listed in the public MCP registry as io.github.26048608982lp-ai/gamenumerics. Game numerical design & balance auditing MCP server, 17 deterministic tools, zero LLM guessing. This page covers its npm package (mcp-server-gamenumerics).

### Is the io.github.26048608982lp-ai/gamenumerics MCP server safe to use?

io.github.26048608982lp-ai/gamenumerics scores 69 out of 100 on VerifyMCP. It declares no install or post-install scripts. 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 io.github.26048608982lp-ai/gamenumerics MCP server expose?

io.github.26048608982lp-ai/gamenumerics exposes 17 tools: list_tables, read_table, battle_simulate, simulate_gacha, compute_power, and 12 more. Their descriptions and schemas cost roughly 2,726 tokens of context every time the server is loaded.

### Is the io.github.26048608982lp-ai/gamenumerics MCP server still maintained?

io.github.26048608982lp-ai/gamenumerics is still listed as active in the MCP registry. We last reached this channel on 20 September 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 io.github.26048608982lp-ai/gamenumerics MCP server under?

io.github.26048608982lp-ai/gamenumerics declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/mcp-server-gamenumerics
- Socket report: https://socket.dev/npm/package/mcp-server-gamenumerics
- Repository: https://github.com/26048608982lp-ai/gamenumerics
- Changelog RSS feed: https://verifymcp.io/servers/26048608982lp-ai-gamenumerics/mcp-server-gamenumerics.xml
- Changelog JSON feed: https://verifymcp.io/servers/26048608982lp-ai-gamenumerics/mcp-server-gamenumerics.json
- HTML version of this page: https://verifymcp.io/servers/26048608982lp-ai-gamenumerics/mcp-server-gamenumerics