io.github.inity13/decisionmatrix-mcp

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Deterministic multi-criteria decision analysis for AI agents — score, rank & explain options.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "decisionmatrix-mcp": {
      "url": "https://decisionmatrix-mcp.pages.dev/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (6)

• create_decision

  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.

  Parameters:

  • options (required) — array — Named alternatives. Strings ["A","B"] or objects [{"name":"A","scores":{...}}].
  • criteria (required) — array — Weighted criteria. Each: {name, weight (relative, >=0), direction: 'benefit' (higher better, default) | 'cost' (lower better)}.
  • scores (required) — object — Score matrix. Object form: {"Option A": {"Criterion 1": 8, ...}, ...}. Array form: [{"option":"Option A","scores":{...}}]. Or inline scores on each option object.
  • method — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• score_options

  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.

  Parameters:

  • options (required) — array — Named alternatives. Strings ["A","B"] or objects [{"name":"A","scores":{...}}].
  • criteria (required) — array — Weighted criteria. Each: {name, weight (relative, >=0), direction: 'benefit' (higher better, default) | 'cost' (lower better)}.
  • scores (required) — object — Score matrix. Object form: {"Option A": {"Criterion 1": 8, ...}, ...}. Array form: [{"option":"Option A","scores":{...}}]. Or inline scores on each option object.
  • method — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• sensitivity_analysis

  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.

  Parameters:

  • options (required) — array — Named alternatives. Strings ["A","B"] or objects [{"name":"A","scores":{...}}].
  • criteria (required) — array — Weighted criteria. Each: {name, weight (relative, >=0), direction: 'benefit' (higher better, default) | 'cost' (lower better)}.
  • scores (required) — object — Score matrix. Object form: {"Option A": {"Criterion 1": 8, ...}, ...}. Array form: [{"option":"Option A","scores":{...}}]. Or inline scores on each option object.
  • steps — integer — Number of weight steps per criterion (2-100).
  • method — string
  • variation — number — Fractional weight sweep, 0<v<=1. 0.2 = +/-20%.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compare_two

  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.

  Parameters:

  • criteria (required) — array — Weighted criteria. Each: {name, weight (relative, >=0), direction: 'benefit' (higher better, default) | 'cost' (lower better)}.
  • scores (required) — object — Score matrix. Object form: {"Option A": {"Criterion 1": 8, ...}, ...}. Array form: [{"option":"Option A","scores":{...}}]. Or inline scores on each option object.
  • method — string
  • options — array — Named alternatives. Strings ["A","B"] or objects [{"name":"A","scores":{...}}].
  • option_a — string
  • option_b — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• health_check

  Server health, version, and capabilities. No parameters.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.