---
title: "idea-reality-mcp"
type: entity
tags: []
last_updated: 2026-04-22
---

## Overview
基于 [[MCP（Model Context Protocol）]] 的竞争分析 MCP 服务器，在 AI 项目启动前扫描 GitHub、Hacker News、npm、PyPI、Product Hunt 五个真实数据源，返回 `reality_signal` 分数（0-100）评估赛道拥挤度，并提供竞品信息和转向建议。

## Type
产品 / MCP Server

## Installation
```bash
uvx idea-reality-mcp
```

## Configuration (OpenClaw)
```json
{
  "mcpServers": {
    "idea-reality": {
      "command": "uvx",
      "args": ["idea-reality-mcp"]
    }
  }
}
```

## API: `idea_check()`
输入：项目想法描述（字符串）
输出：
- `reality_signal`：0-100 拥挤度评分
- `top_competitors`：竞品列表（含 stars、描述）
- `pivot_hints`：转向建议

## Usage Rules (OpenClaw Instructions)
```
Before starting any new project, feature, or tool, always run idea_check first.

Rules:
- If reality_signal > 70: STOP. Report top 3 competitors with star counts.
  Ask if I want to proceed, pivot, or abandon.
- If reality_signal 30-70: Show results and pivot_hints.
  Suggest a niche angle that existing projects don't cover.
- If reality_signal < 30: Proceed to build.
  Mention that the space is open.
- Always show the reality_signal score and top competitors before writing any code.
```

## Data Sources
- GitHub（仓库数量、Star 分布）
- Hacker News（讨论热度）
- npm（Node.js 包生态）
- PyPI（Python 包生态）
- Product Hunt（早期产品关注度）

## Related
- [[Pre-Build Validation]]
- [[Competition-Analysis]]
- [[MCP（Model Context Protocol）]]
- [[OpenClaw]]
- [GitHub](https://github.com/mnemox-ai/idea-reality-mcp)
- [PyPI](https://pypi.org/project/idea-reality-mcp/)
- [Web Demo](https://mnemox.ai/check)