decisionmatrix-mcp
Deterministic multi-criteria decision analysis for AI agents — score, rank & explain options.
我该使用它吗
质量与安全性
发现（2）
- LOWTool 'compare_two' description lacks action verb在 compare_two 中
- LOWTool 'health_check' description lacks action verb在 health_check 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"decisionmatrix-mcp": {
"command": "npx",
"args": [
"decisionmatrix-mcp"
]
}
}
}可运行的软件包
1.0.2stdio远程端点
https://decisionmatrix-mcp.pages.dev/mcpstreamable-http它能做什么
工具清单
工具（6）
🟡create_decision(options, criteria, scores, method)
Rank named options against weighted criteria and return the winner, full ranking, per-criterion score breakdowns, methodology, the weights used, and a plain-language explanation. This is the main tool. Provide options, criteria [{name, weight, direction}], and a scores matrix. method defaults to weighted_sum (also: weighted_product, topsis). 100% deterministic.
输入模式
{
"type": "object",
"properties": {
"options": {
"type": "array",
"description": "Named alternatives. Strings [\"A\",\"B\"] or objects [{\"name\":\"A\",\"scores\":{...}}].",
"items": {
"type": [
"string",
"object"
]
}
},
"criteria": {
"type": "array",
"description": "Weighted criteria. Each: {name, weight (relative, >=0), direction: 'benefit' (higher better, default) | 'cost' (lower better)}.",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"weight": {
"type": "number"
},
"direction": {
"type": "string",
"enum": [
"benefit",
"cost"
],
"default": "benefit"
}
},
"required": [
"name",
"weight"
]
}
},
"scores": {
"description": "Score matrix. Object form: {\"Option A\": {\"Criterion 1\": 8, ...}, ...}. Array form: [{\"option\":\"Option A\",\"scores\":{...}}]. Or inline scores on each option object.",
"type": "object"
},
"method": {
"type": "string",
"enum": [
"weighted_sum",
"weighted_product",
"topsis"
],
"default": "weighted_sum"
}
},
"required": [
"options",
"criteria",
"scores"
]
}🟡score_options(options, criteria, scores, method)
Score options against criteria when the score matrix is supplied separately. Returns the full normalized scored matrix (per-option, per-criterion) plus a ranking, without the narrative winner explanation. Use create_decision if you want a winner + explanation.
输入模式
{
"type": "object",
"properties": {
"options": {
"type": "array",
"description": "Named alternatives. Strings [\"A\",\"B\"] or objects [{\"name\":\"A\",\"scores\":{...}}].",
"items": {
"type": [
"string",
"object"
]
}
},
"criteria": {
"type": "array",
"description": "Weighted criteria. Each: {name, weight (relative, >=0), direction: 'benefit' (higher better, default) | 'cost' (lower better)}.",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"weight": {
"type": "number"
},
"direction": {
"type": "string",
"enum": [
"benefit",
"cost"
],
"default": "benefit"
}
},
"required": [
"name",
"weight"
]
}
},
"scores": {
"description": "Score matrix. Object form: {\"Option A\": {\"Criterion 1\": 8, ...}, ...}. Array form: [{\"option\":\"Option A\",\"scores\":{...}}]. Or inline scores on each option object.",
"type": "object"
},
"method": {
"type": "string",
"enum": [
"weighted_sum",
"weighted_product",
"topsis"
],
"default": "weighted_sum"
}
},
"required": [
"options",
"criteria",
"scores"
]
}⚪sensitivity_analysis(options, criteria, scores, method, variation, ...)
Test how robust the winner is to changes in criteria weights. Sweeps each criterion's weight +/- 'variation' (default 0.2 = 20%) over 'steps' (default 10) increments, recomputes the ranking, and reports a robustness score, which criteria are most likely to flip the result, and the flip points.
输入模式
{
"type": "object",
"properties": {
"options": {
"type": "array",
"description": "Named alternatives. Strings [\"A\",\"B\"] or objects [{\"name\":\"A\",\"scores\":{...}}].",
"items": {
"type": [
"string",
"object"
]
}
},
"criteria": {
"type": "array",
"description": "Weighted criteria. Each: {name, weight (relative, >=0), direction: 'benefit' (higher better, default) | 'cost' (lower better)}.",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"weight": {
"type": "number"
},
"direction": {
"type": "string",
"enum": [
"benefit",
"cost"
],
"default": "benefit"
}
},
"required": [
"name",
"weight"
]
}
},
"scores": {
"description": "Score matrix. Object form: {\"Option A\": {\"Criterion 1\": 8, ...}, ...}. Array form: [{\"option\":\"Option A\",\"scores\":{...}}]. Or inline scores on each option object.",
"type": "object"
},
"method": {
"type": "string",
"enum": [
"weighted_sum",
"weighted_product",
"topsis"
],
"default": "weighted_sum"
},
"variation": {
"type": "number",
"default": 0.2,
"description": "Fractional weight sweep, 0<v<=1. 0.2 = +/-20%."
},
"steps": {
"type": "integer",
"default": 10,
"description": "Number of weight steps per criterion (2-100)."
}
},
"required": [
"options",
"criteria",
"scores"
]
}⚪compare_two(option_a, option_b, options, criteria, scores, ...)
Direct head-to-head comparison of exactly two options. Returns the winner, the score margin, how many criteria each option wins, and a per-criterion breakdown of who each criterion favours. Pass option_a and option_b (names) or a 2-element options array, plus criteria and scores.
输入模式
{
"type": "object",
"properties": {
"option_a": {
"type": "string"
},
"option_b": {
"type": "string"
},
"options": {
"type": "array",
"description": "Named alternatives. Strings [\"A\",\"B\"] or objects [{\"name\":\"A\",\"scores\":{...}}].",
"items": {
"type": [
"string",
"object"
]
}
},
"criteria": {
"type": "array",
"description": "Weighted criteria. Each: {name, weight (relative, >=0), direction: 'benefit' (higher better, default) | 'cost' (lower better)}.",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"weight": {
"type": "number"
},
"direction": {
"type": "string",
"enum": [
"benefit",
"cost"
],
"default": "benefit"
}
},
"required": [
"name",
"weight"
]
}
},
"scores": {
"description": "Score matrix. Object form: {\"Option A\": {\"Criterion 1\": 8, ...}, ...}. Array form: [{\"option\":\"Option A\",\"scores\":{...}}]. Or inline scores on each option object.",
"type": "object"
},
"method": {
"type": "string",
"enum": [
"weighted_sum",
"weighted_product",
"topsis"
],
"default": "weighted_sum"
}
},
"required": [
"criteria",
"scores"
]
}🟢list_methods
List the available scoring methods (weighted_sum, weighted_product, topsis) with descriptions, normalization details, score ranges, and when to use each. No parameters.
输入模式
{
"type": "object",
"properties": {}
}🟢health_check
Server health, version, and capabilities. No parameters.
输入模式
{
"type": "object",
"properties": {}
}社区
证据