INDIVIDUAL MCP TOOL

analyze_reviews

深度分析一批评论，输出结构化 VOC 报告：核心痛点、功能诉求、好评点、紧急度、行动建议。基于 DeepSeek 语义分析，只依据你传入的评论原文，不编造数据；引用评论原话作为证据。未配置 DEEPSEEK_API_KEY 时自动降级为本地 extract_voice_of_customer 结果。

goaimoat.comnone authenticationAvailability not checked

LIVE ENDPOINT

https://reviewintel.mcp.goaimoat.com/mcp

No auth detected

Connect to this endpoint to inspect the live schema for analyze_reviews and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

Parent server

goaimoat.com

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.goai-moat-review-intelligence]
url = "https://reviewintel.mcp.goaimoat.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "goai-moat-review-intelligence": {
      "type": "http",
      "url": "https://reviewintel.mcp.goaimoat.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: goai-moat-review-intelligence
Remote MCP URL: https://reviewintel.mcp.goaimoat.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "goai-moat-review-intelligence": {
      "url": "https://reviewintel.mcp.goaimoat.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "goai-moat-review-intelligence": {
      "type": "http",
      "url": "https://reviewintel.mcp.goaimoat.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "goai-moat-review-intelligence",
  "transport": "streamable-http",
  "url": "https://reviewintel.mcp.goaimoat.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

Related tools

extract_voice_of_customer — 零成本本地分析一批产品评论：情感占比 + 高频关键词 + 差评痛点句子。确定性算法（词频 + 中英情感词典），不调用任何外部 API，永远可用、可复现。输入是一批评论原文（每行一条，或用 | 分隔），不是评论链接——本工具分析你给的内容。
competitive_gap — 对比两批评论，找出竞对差距：A 有 B 无、B 有 A 无、差异化机会。典型用法：name_a=你的产品评论、name_b=竞品评论，看竞品被夸但你被骂的点（=你必须补的），以及你被夸但竞品被骂的点（=你的卖点）。基于 DeepSeek 语义分析。