Search Intent MCP
# Search Intent MCP
请通过 https://aisearchintent.com 获取 API key
这是一个基于 MCP (Model Context Protocol) 的搜索意图分析服务。它可以帮助分析用户搜索关键词的意图,为 SEO 分析提供支持。
## 功能特点
- 分析搜索关键词的意图
- 提供可能的分类
- 提供推理过程
- 提供相关参考链接
- 提供搜索建议
## 使用方法
### claude 安装
```json
{
"mcpServers": {
"search_intent": {
"command": "npx",
"args": ["-y", "@search-intent/mcp"],
"env": {
"SEARCH_INTENT_API_KEY": "xxx"
}
}
}
}
```
## 开发
```bash
# 克隆仓库
git clone
# 安装依赖
pnpm install
# 设置环境变量
export SEARCH_INTENT_API_KEY=your_api_key
```
## API 使用示例
服务提供了一个名为 `search_intent_analysis` 的工具,可以这样使用:
```json
{
"name": "search_intent_analysis",
"arguments": {
"query": "grok3"
}
}
```
返回结果示例:
```json
{
"query": "grok3",
"intent": "Information Lookup about xAI's Grok 3...",
"possibleCategories": [
"AI Model",
"Technology",
"Chatbot",
"Product Information"
],
"reasoning": "The user is likely trying to understand...",
"references": [
{
"url": "https://example.com",
"title": "Example Title"
}
],
"searchSuggestions": [
"grok3 meaning",
"grok3 search intent",
"grok3 categories",
"grok3"
]
}
```
TDQS
Scored across 1 tool
With only one tool, there is no ambiguity or overlap between tools. The tool has a clear, singular purpose focused on search intent analysis, making it impossible for an agent to misselect between non-existent alternatives.
The single tool name follows a consistent snake_case pattern (search_intent_analysis). Since there is only one tool, naming consistency is inherently perfect with no deviations or mixed conventions to evaluate.
A single tool is too few for a server named 'Search Intent MCP', which suggests a broader scope for search-related operations. While the tool covers analysis well, the set lacks complementary tools for actions like refining searches, tracking trends, or managing intents, making it feel thin and incomplete for the domain.
The tool surface is severely incomplete for search intent analysis. It only provides analysis without supporting operations like saving intents, comparing queries over time, or integrating with search engines. This creates significant gaps that will limit agent workflows, as analysis alone is a dead end without follow-up actions.