Positioning
Based on Xiyou Insight MCP , an Amazon competitor analysis and advertising strategy tool. The LLM Agent directly calls MCP tools to obtain data, while scripts are only responsible for data post-processing, report generation, and visual rendering.
Core Features:
- MCP-driven: All data acquisition is directly called through xydc-mcp
- Scenario-based workflows: 7 core scenarios covering advertising monitoring, traffic analysis, competitor breakdown, new product promotion, and keyword library building
- Lightweight scripts: Used only for data aggregation, report generation, and Dashboard rendering
MCP Tool Quick Reference
ASIN Basic Information
| Tool Name | Function | Parameters |
|---|---|---|
get_asin_info |
Get ASIN basic information (title, price, rating, review count, main image) | asins, country |
get_asin_variations |
Query parent-child variation relationships | asin, country |
get_asin_info_trends |
Daily product information trends (price, rating, review count changes) | asin, country, start_date, end_date |
ASIN Keyword Analysis
| Tool Name | Function | Parameters |
|---|---|---|
get_asin_keywords |
ASIN reverse keyword lookup (last 7 days) | asin, country, page, page_size, sort_field, sort_order |
get_asin_keywords_monthly |
ASIN reverse keyword lookup (monthly history) | asin, country, start_month, end_month, page, page_size |
get_asin_keyword_rank_trends |
Keyword daily ranking trend | asin, keyword, country, start_date, end_date |
get_asin_keyword_rank_hourly |
Keyword hourly ranking (US/UK/DE only) | asin, keyword, country, date |
get_asin_keyword_traffic_trends |
Keyword daily traffic trend | asin, keyword, country, start_date, end_date |
ASIN Traffic and Sales
| Tool Name | Function | Parameters |
|---|---|---|
get_asin_traffic |
Traffic score for the last 7 days (organic/ad traffic share) | asins, country |
get_asin_traffic_trends |
Daily traffic trend (organic/ad/position dimensions) | asin, country, start_date, end_date |
get_asin_order_trends |
Monthly order volume trend | asin, country, start_month, end_month |
get_asin_bsr_trends |
Daily BSR category ranking trend | asin, country, start_date, end_date |
ASIN Advertising Analysis
| Tool Name | Function | Parameters |
|---|---|---|
get_asin_ad_change_trends |
Daily trends in advertising placement changes (added/removed campaigns) | asin, country, start_date, end_date |
Keyword Analysis
| Tool Name | Function | Parameters |
|---|---|---|
get_keyword_info |
Keyword basic metrics (search volume, competition difficulty, suggested bid) | keywords, country |
get_keyword_aba_trends |
ABA search volume weekly trend (up to 52 weeks) | keywords, country, start_week, end_week |
get_keyword_asin_analysis |
Keyword reverse ASIN lookup (last 7 days competitive landscape) | keyword, country, page, page_size, sort_field, sort_order |
get_keyword_analysis_monthly |
Monthly history of keyword competitive landscape | keyword, country, start_month, end_month, page, page_size |
7 Core Work Scenarios
Scenario 1: Real-time Monitoring of Advertising Performance
Objective: Monitor advertising performance in real time through hourly ranking changes and ad projector
Workflow:
Step 1: 获取ASIN基础信息
→ get_asin_info(asin)
Step 2: 查询小时级排名(仅US/UK/DE)
→ get_asin_keyword_rank_hourly(asin, keyword, date)
分析广告排名位置和持续时间
Step 3: 查询日排名趋势
→ get_asin_keyword_rank_trends(asin, keyword, start_date, end_date)
判断广告投放带动自然排名上升情况
Step 4: 查询广告投放变化
→ get_asin_ad_change_trends(asin, start_date, end_date)
分析广告活动新增/移除情况
Step 5: 生成分析报告
→ 评估广告投放效率,判断是否带来自然排名提升
Output: Advertising performance analysis report
Scenario 2: Quickly Find High-Cost-Performance Traffic Gaps
Objective: Through multi-ASIN comparison and keyword analysis, find traffic gaps where competitors have rankings but you do not
Workflow:
Step 1: 获取多个ASIN基础信息
→ get_asin_info(asins)
Step 2: 获取各ASIN关键词列表
→ get_asin_keywords(asin1)
→ get_asin_keywords(asin2)
→ ...
Step 3: 对比关键词覆盖差异
→ 找出竞品有排名但自身没有的关键词
Step 4: 分析关键词竞争程度
→ get_keyword_info(keywords)
判断搜索量、竞争难度、建议竞价
Step 5: 分析关键词下ASIN竞争格局
→ get_keyword_asin_analysis(keyword)
判断自然位滚动率、广告位竞争难度
Step 6: 筛选高性价比流量缺口
→ 综合评估:搜索量中等、竞争难度低、竞品有排名但自身无排名
Output: Traffic gap analysis report, including a list of recommended keywords to add
Scenario 3: Quickly break down benchmark competitors' strategies
Objective: Comprehensively analyze competitors' keyword coverage differences, traffic structure, and advertising strategies
Workflow:
Step 1: 获取竞品基础信息
→ get_asin_info(competitor_asins)
Step 2: 确认主推变体
→ get_asin_variations(asin)
确定父体下流量最大的变体
Step 3: 分析流量结构
→ get_asin_keywords(asin)
→ get_asin_traffic(asin)
分析头部词、腰部词、长尾词贡献的展示量
Step 4: 分析广告策略
→ get_asin_ad_change_trends(asin, start_date, end_date)
→ get_asin_traffic_trends(asin, start_date, end_date)
了解广告流量构成和广告展示位置关键词
Step 5: 趋势分析
→ get_asin_keyword_rank_trends(asin, keyword, start_date, end_date)
洞察竞品广告投放策略和节奏
Step 6: 综合对比分析
→ 关键词覆盖差异、流量份额、广告策略对比
Output: Competitor strategy breakdown report
Scenario 4: Improve new product promotion efficiency
Objective: Analyze the new product traffic allocation stages (sparse period → fluctuation period → stable period), and seize opportunities from anomalous keywords
Workflow:
Step 1: 获取ASIN基础信息
→ get_asin_info(asin)
Step 2: 分析流量趋势
→ get_asin_traffic_trends(asin, start_date, end_date)
判断流量分配阶段:稀疏期/震荡期/稳定期
Step 3: 分析关键词排名变化
→ get_asin_keywords(asin)
→ get_asin_keyword_rank_trends(asin, keyword, start_date, end_date)
Step 4: 识别异动关键词
- 新增:昨日无排名今日出现排名
- 流失:昨日有排名今日消失
- 流量升档:自然流量上升(稀疏→震荡→稳定)
- 流量降档:自然流量下降
Step 5: 把握流量窗口机会
→ 针对新增和流量升档关键词加大投放
→ 针对流失和流量降档关键词分析原因并调整
Output: New product promotion analysis report, including traffic stage assessment and suggestions for anomalous keywords
Scenario 5: Precisely break down competitor traffic and advertising strategies
Objective: In-depth analysis of competitors' keyword layout, traffic sources, and ad placement strategies
Workflow:
Step 1: 获取竞品基础信息
→ get_asin_info(competitor_asins)
Step 2: 确认主推变体
→ get_asin_variations(asin)
Step 3: 分析关键词布局
→ get_asin_keywords(asin)
→ get_asin_keywords_monthly(asin, start_month, end_month)
了解关键词覆盖广度和月度变化
Step 4: 分析流量结构
→ get_asin_traffic(asin)
→ get_asin_traffic_trends(asin, start_date, end_date)
自然/广告流量占比、位置维度拆解
Step 5: 分析广告策略
→ get_asin_ad_change_trends(asin, start_date, end_date)
→ get_asin_keyword_traffic_trends(asin, keyword, start_date, end_date)
Step 6: 关键词竞争分析
→ get_keyword_info(keywords)
→ get_keyword_asin_analysis(keyword)
分析竞品核心关键词的竞争格局
Step 7: 生成综合分析报告
→ 关键词覆盖差异、流量结构、广告策略洞察
Output: In-depth analysis report on competitor traffic and advertising strategies
Scenario 6: Gain insight into competitor advertising strategies and budgets
Objective: Analyze competitors' ad type distribution, campaign structure, budget distribution, and core advertising keywords
Workflow:
Step 1: 获取竞品基础信息
→ get_asin_info(asin)
Step 2: 确认主推变体
→ get_asin_variations(asin)
Step 3: 分析广告活动变化
→ get_asin_ad_change_trends(asin, start_date, end_date)
识别新增/移除的广告活动,分析投放节奏
Step 4: 分析流量趋势
→ get_asin_traffic_trends(asin, start_date, end_date)
判断SP/SB/SBV广告流量占比
Step 5: 分析关键词流量贡献
→ get_asin_keywords(asin)
→ get_asin_keyword_traffic_trends(asin, keyword, start_date, end_date)
找出核心广告关键词及其流量占比
Step 6: 推断预算分布
→ 根据广告展示时长和关键词流量变化推断预算调整
→ 分析广告投放的周期性规律
Step 7: 生成广告策略分析报告
→ 广告类型分布、活动结构、核心关键词、预算推断
Output: Competitor advertising strategy and budget analysis report
Scenario 7: Efficiently build a keyword library
Objective: Build a complete keyword library by reverse-looking up competitor traffic keywords and finding keywords by keyword
Workflow:
Step 1: 广泛收集关键词
→ 方式1:反查竞品流量词
get_asin_keywords(competitor_asin) × 多个竞品
→ 方式2:关键词基础信息
get_keyword_info(core_keywords)
Step 2: 关键词拓展
→ get_keyword_aba_trends(keywords, start_week, end_week)
分析搜索量趋势和季节性
Step 3: 关键词竞争分析
→ get_keyword_asin_analysis(keyword)
判断每个关键词下的竞争格局
Step 4: 按相关性筛选
→ 强/高/中相关 → 加入关键词库
→ 低/极低相关 → 加入否定词库
Step 5: 关键词分类
→ 数据维度:搜索量(大/中/小)、竞争难度(超难/难/中等/简单)、转化率(高/中/低)
→ 属性维度:人群受众、使用场景、产品维度、价值维度
Step 6: 输出关键词库
→ 结构化关键词列表,包含分类标签和优先级
Output: Complete keyword library, including keyword classification and priority annotations
Script Directory
| Script | Purpose | When to call |
|---|---|---|
report_generator.py |
Report generator: Aggregate MCP data into a Markdown report | After each scenario is completed |
dashboard_generator.py |
Dashboard rendering: Generate visualization dashboard HTML | After the report is generated |
data_aggregator.py |
Data aggregator: Merge multiple ASIN/keyword data | Multi-ASIN comparison scenarios |
Script responsibilities:
- Do not make API calls: All data retrieval is called directly by the LLM through MCP
- Only perform data processing: Aggregation, cleaning, formatting
- Report rendering: Generate Markdown and HTML reports
Execution flow
General execution mode
1. 用户输入场景和参数(ASIN/关键词/站点)
2. LLM根据场景选择对应MCP工具组合
3. 调用MCP工具获取数据
4. 使用脚本进行数据后处理和报告生成
5. 输出Markdown报告和Dashboard看板
Data output directory
xiyou-insight-reports/
└── {scenario}_{asin_or_keyword}_{site}_{YYYYMMDD}/
├── report.md # Markdown完整报告
├── data.json # 结构化数据
├── dashboard.html # 可视化看板
└── raw/ # 原始MCP响应数据
├── asin_info.json
├── keywords.json
├── traffic.json
└── ad_trends.json
Data field naming conventions
| Field name | Description | Example |
|---|---|---|
natural_traffic |
Organic traffic score | 85.5 |
ad_traffic |
Ad traffic score | 42.3 |
total_traffic |
Total traffic score | 127.8 |
keyword_count |
Keyword count | 156 |
natural_rank |
Organic ranking position | 5 |
ad_rank |
Ad ranking position | 2 |
weekly_search_volume |
Weekly search volume | 125000 |
competitive_difficulty |
Competition difficulty (0-100) | 72 |
cost_per_click |
Suggested bid | 2.35 |
Supported marketplaces
US, CA, MX, BR, UK, DE, FR, ES, IT, JP, AE, AU, SA
Note: Hourly rankings (get_asin_keyword_rank_hourly) are only supported for US/UK/DE marketplaces
Precautions
- API rate limiting: It is recommended to control the number of concurrent requests per batch to avoid triggering rate limiting
- Data timeliness: Data from the last 7 days has good real-time performance; historical data may be delayed
- Consumption Notice: The longer the query date range, the higher the API consumption
- intent_summary: All MCP calls must include a desensitized description of the business intent; including the user's original prompt, account, phone number, email, or full ASIN is prohibited
Relationship with Other Skills
category-selection (品类筛选)
↓
product-research (深度选品调研)
↓
xiyou-insight (竞品分析与广告策略) ← 本Skill
↓
review-analysis (评论深度分析)
Differences:
category-selection: Quick screening at the category levelproduct-research: In-depth research on a specified categoryxiyou-insight: Competitor traffic analysis and ad strategy breakdownreview-analysis: In-depth pain point analysis of reviews
Version: v1.0 (7-scenario workflow) | Last updated: 2026-07-04