Log inSubmit server
Decisionkit logo

Decisionkit

by @adxtya21

Probability-scored binary, choice, scoring, and ranking decisions through an MCP server, CLI, or Claude Code plugin.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Decisionkit

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "adxtya21-decisionkit": {
      "command": "npx",
      "args": [
        "-y",
        "@adxtya21/decisionkit"
      ],
      "env": {
        "DECISIONKIT_PROVIDER": "YOUR_VALUE_HERE",
        "DECISIONKIT_OPENAI_API_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Automated check passed— started and listed 2 tools correctly (Today).

Overview

@adxtya21/decisionkit exposes probability-scored decisions through MCP tools, a CLI, and a Claude Code plugin. Use it when an agent or automation needs structured classification, threshold checks, severity scoring, or candidate ranking rather than a prose response. The MCP interface provides decision and status operations for supported AI clients.

Use cases

  • Classify software issues as bugs, features, refactors, or documentation
  • Check whether a code diff breaks a public API
  • Score incident severity from ordered levels
  • Rank files by relevance to a reported bug

Key features

  • Binary, choice, score, and rank decisions
  • Per-answer probability estimates
  • OpenAI Decisions API, Jev, OpenRouter, and Claude providers
  • MCP, CLI, and Claude Code plugin interfaces
  • Threshold-based exit codes for scripts and CI
  • JSON, plain, and formatted CLI output

Tools2

What Decisionkit lets your agent do. Expand a tool for its parameters.

Verified live~871 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

What it can do

From the 2 tools this server returned when we ran it; 2 declare their own safety hints.

Handles credentials · 2Makes network requests · 2Read-only tools · 2
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceNot published
Package age30 days
Maintainers1

Observed 2026-11-09 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 14h ago via OSV.dev · @adxtya21/decisionkit (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars8Stargazers on the source repository.
npm downloads1.2kPackage downloads in the last 30 days.
Last commit1mo agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed2Callable tools this server registers over MCP.

How Decisionkit works

What @adxtya21/decisionkit does

@adxtya21/decisionkit turns questions about text into structured decisions. It supports four decision forms:

  • Binary questions return a probability for true.
  • Choice questions select from 2–255 options and return a probability for each option.
  • Score questions place an item on 2–10 ordered levels and return the expected level, most likely level, and per-level probabilities.
  • Rank questions order 2–20 candidates using one score per candidate.

The package is available as an MCP server, a command-line program, and a Claude Code plugin. MCP clients can use it for issue triage, API-change checks, incident severity assessment, and ranking files or other candidates against a piece of context.

How it works

Each request sends its context and question to the single provider selected in configuration. Supported providers are Claude through the existing Claude Code login, the OpenAI Decisions API, Jev from TypeSafe AI, and Jev through OpenRouter. Results identify the provider and model; the CLI reports that information on stderr.

The MCP interface exposes a decide operation for decisions and a status operation for provider connectivity and usage information. The CLI reads context from standard input or a --context option. Running decisionkit without arguments starts the MCP server.

Decision probabilities are estimates from the selected provider and are not presented as calibrated probabilities. Ranking is derived from separate candidate scores, so nearby scores should be treated as ties. The system returns provider-specific fields under native and does not generate rationales.

Setup and configuration

Node.js 20 or newer must be available on the PATH. Install the package globally with:

Terminal
npm i -g @adxtya21/decisionkit

Set DECISIONKIT_PROVIDER to claude, openai, jev, or openrouter. The OpenAI quickstart uses DECISIONKIT_OPENAI_API_KEY; Claude uses the existing Claude Code login and does not require an additional API key. Provider credentials are selected explicitly rather than taken from generic OPENAI_API_KEY or OPENROUTER_API_KEY variables.

The Claude Code plugin can be installed from the project's marketplace and configured with /plugin configure decisionkit@decisionkit. Plugin settings include the provider, provider key, model, timeout, and local usage logging. Keys entered through the plugin are masked and stored in the operating system's secure store.

Tools and capabilities

The CLI includes binary, choice, score, rank, and status commands. Binary, choice, and score operations support thresholds for automation. Exit code 0 indicates a true or sufficiently confident result, 1 indicates false or below threshold, and 2 indicates configuration, network, or provider failure.

Terminal output includes probability bars and a provider footer, while piped output uses a plain format. --json returns the complete result, --pretty and --plain select display modes, and --quiet hides the provider disclosure line. A local usage log records identifiers, timings, token counts, and estimated cost without prompt content.

Limitations and notes

Context is sent to the configured third-party provider, so secrets, credentials, personal data, and uncleared code should be excluded. Agents call the tool only when they choose to; content is not sent elsewhere automatically. Claude Code displays the exact payload in a permission prompt, while other clients may auto-approve tools.

A standalone CLI process creates a fresh provider connection on every run, making repeated calls slower than a persistent MCP process. Failures, refusals, and invalid provider responses are errors rather than decision results. Thresholds should be selected using labeled examples appropriate to the task.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Decisionkit

@adxtya21/decisionkit is an MCP server that connects AI clients to Claude Code, the OpenAI Decisions API, Jev, or Jev through OpenRouter. Its main tools make binary, multiple-choice, scoring, and ranking decisions with probability estimates, while a status tool reports provider connectivity and usage information.

Install Node.js 20 or newer, then run `npm i -g @adxtya21/decisionkit`. Set `DECISIONKIT_PROVIDER` to a supported provider and configure its credentials where needed. Running `decisionkit` without arguments starts the MCP server.

It supports Claude through a Claude Code login, the OpenAI Decisions API, Jev from TypeSafe AI, and Jev through OpenRouter. Select one with `DECISIONKIT_PROVIDER`; the selected provider receives the decision context and questions.

Yes, Cursor is listed as a supported MCP client. Configure the MCP server in Cursor with Node.js 20 or newer available and provide the required provider configuration.

No. It returns structured decisions and probability estimates rather than rationales. Provider-specific fields remain available under `native`, but decisionkit does not create an explanation.

Related MCP servers

All in Developer Tools All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewDecisionkit AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/adxtya21-decisionkit?style=directory)](https://allmcps.com/mcp/adxtya21-decisionkit)
HTML Embed
<a href="https://allmcps.com/mcp/adxtya21-decisionkit"><img src="https://allmcps.com/api/badge/adxtya21-decisionkit?style=directory" alt="Decisionkit on AllMCPs" /></a>