amidabuddha/jev-decision-mcp

开发工具

本页由 AI 翻译，技术细节请以原文为准。查看原文

1 stars 0 forks 质量 79 趋势 16MIT

Repository Install

本地MCP服务器用于TypeSafe jev类型决策，并集成Codex。

概览

本地的stdio MCP服务器，通过任何兼容SDK的决策API端点，暴露一个工具，用于类型决策。指向带有BASE_URL和MODEL的端点;没有提供者预设、主机允许列表或模型允许列表。用TypeScript编写，使用官方MCP SDK和@typesafe-ai/sdk类型决策SDK。独立社区项目;与SDK供应商无关。授权在麻省理工学院（MIT）下。在同一通话中批量处理同一上下文下的问题。答案保留其问题ID。MCP返回判决和令牌使用情况;呼叫者拥有阈值、升级和动作执行。 - Node.js 22或更新版本，且可在你的PATH上提供npm。- 支持本地stdio服务器的MCP客户端。- 用于你配置的决策端点（API_KEY）的API密钥。该密钥仅用于决策调用——工具可在无需调用的情况下被发现。

概述（AI 翻译）

本地的stdio MCP服务器通过一个工具**jev_decide**，用于通过任何兼容SDK的决策API端点进行类型决策。指向具有BASE_URL和MODEL的端点;没有提供者预设、主机允许列表或模型允许列表。用TypeScript编写，使用官方MCP SDK和@typesafe-ai/sdk类型决策SDK。

独立社区项目;与SDK供应商无关。授权在麻省理工学院（MIT）下。

问题	用它来做	结果
`choice`	选择标签或候选	选择、概率、信心
`score`	在2至10个有序层级上对单一维度进行评分	基于0的得分、概率、图例、置信度
`noul`	判断条件是否成立	是的概率，从0到1

在同一通话中批量处理同一上下文下的问题。答案保留其问题ID。MCP返回判决和令牌使用情况;呼叫者拥有阈值、升级和动作执行。

要求

Node.js 22 或更新版本，NPM 可在你的 PATH 上使用。
支持本地标准服务器的MCP客户端。
你配置的决策端点的API密钥（API_KEY。

本页由 AI 翻译，技术细节请以原文为准。

README

以下为原文 README 节选，完整内容请查看原文。

Jev Decision MCP

A local stdio MCP server exposing one tool, jev_decide, for typed decisions through any SDK-compatible decision API endpoint. Point it at an endpoint with BASE_URL and MODEL; there is no provider preset, host allowlist, or model allowlist. Written in TypeScript with the official MCP SDK and the @typesafe-ai/sdk typed-decision SDK.

Independent community project; not affiliated with the SDK vendor. Licensed under MIT.

Question	Use it for	Result
`choice`	Choose a label or candidate	Choice, probabilities, confidence
`score`	Rate a single dimension on 2–10 ordered levels	0-based score, probabilities, legend, confidence
`noul`	Judge whether a condition holds	Probability of yes, from 0 to 1

Batch independent questions over the same context in one call. Answers retain their question IDs. The MCP returns judgments and token usage; the caller owns thresholds, escalation, and action execution.

Requirements

Node.js 22 or newer, with npm available on your PATH.
An MCP client that supports local stdio servers.
An API key for the decision endpoint you configure (API_KEY). It is required for decision calls only — the tool can be discovered without one.

What “SDK-compatible” means here. Compatibility is the typed-decision contract of the @typesafe-ai/sdk: the endpoint must implement the SystemOne request (POST {BASE_URL}/v1/systemone) that returns typed choice/score/noul answers with probability distributions and usage counts.

Install from npm

The npm package includes the built server. npx downloads it on first use and runs it without cloning or building:

npx -y [email protected]

Add the following to your MCP client’s configuration, replacing the placeholders with your endpoint’s values. For clients that use mcpServers JSON:

{
  "mcpServers": {
    "jev": {
      "command": "npx",
      "args": ["-y", "[email protected]"],
      "env": {
        "API_KEY": "YOUR_API_KEY",
        "BASE_URL": "https://api.example.com/decisions",
        "MODEL": "your-model-name"
      }
    }
  }
}

Alternatively, set API_KEY, BASE_URL, and MODEL in the environment that launches your client and omit env if the client forwards those variables. Restart or reload your client’s MCP servers after saving the configuration; the tool appears as jev_decide.

If the host cannot resolve npx, use its platform-specific launcher or absolute path as documented by that host. GUI applications may have a different PATH from your terminal.

The server communicates over stdio; starting it in a terminal waits for an MCP

在 GitHub 查看完整 README

安装

npx -y [email protected]

新手？先看 mcpskill.org 教程 →

配置

{
  "mcpServers": {
    "jev": {
      "command": "npx",
      "args": ["-y", "[email protected]"],
      "env": {
        "API_KEY": "YOUR_API_KEY",
        "BASE_URL": "https://api.example.com/decisions",
        "MODEL": "your-model-name"
      }
    }
  }
}