diff --git a/README-EN.md b/README-EN.md
index e31e3bf..05b40f4 100644
--- a/README-EN.md
+++ b/README-EN.md
@@ -47,7 +47,7 @@
| [🎯 Core Features](#-core-features) | [🚀 Quick Start](#-quick-start) | [🐳 Docker Deployment](#-docker-deployment) | [🤖 AI Analysis](#-ai-analysis-deployment) |
|:---:|:---:|:---:|:---:|
| [📝 Changelog](#-changelog) | [🔌 MCP Clients](#-mcp-clients) | [❓ FAQ & Support](#-faq--support) | [⭐ Related Projects](#-related-projects) |
-| [🔧 Custom Platforms](#custom-monitoring-platforms) | [📝 Keywords Config](#frequencywordstxt-configuration) | | |
+| [🔧 Custom Platforms](#custom-monitoring-platforms) | [📝 Keywords Config](#frequencywordstxt-configuration) | [🪄 Sponsors](#-sponsors) | |
@@ -102,8 +102,6 @@ This project uses the API from [newsnow](https://github.com/ourongxing/newsnow)
-> This project uses the API from [newsnow](https://github.com/ourongxing/newsnow) to fetch multi-platform data
-
## ✨ Core Features
### **Multi-Platform Trending News Aggregation**
@@ -474,7 +472,11 @@ AI conversational analysis system based on MCP (Model Context Protocol), enablin
- Cross-platform data comparison (activity stats, keyword co-occurrence)
- Smart summary generation, similar news finding, historical correlation search
-> No more manual data file browsing—AI assistant helps you understand the stories behind the news in seconds
+> **💡 Usage Tip**: AI features require local news data support
+> - Project includes **November 1-15** test data for immediate experience
+> - Recommend deploying the project yourself to get more real-time data
+>
+> See [AI Analysis Deployment](#-ai-analysis-deployment) for details
### **Zero Technical Barrier Deployment**
@@ -904,7 +906,41 @@ frequency_words.txt file added **required word** feature, using + sign
- **Method 2:** (See Chinese version for detailed steps)
+ **Method 2:**
+
+ 1. Open in PC browser https://botbuilder.feishu.cn/home/my-app
+
+ 2. Click "New Bot Application"
+
+ 3. After entering the created application, click "Process Design" > "Create Process" > "Select Trigger"
+
+ 4. Scroll down, click "Webhook Trigger"
+
+ 5. Now you'll see "Webhook Address", copy this link to local notepad temporarily, continue with next steps
+
+ 6. In "Parameters" put the following content, then click "Done"
+
+ ```json
+ {
+ "message_type": "text",
+ "content": {
+ "total_titles": "{{Content}}",
+ "timestamp": "{{Content}}",
+ "report_type": "{{Content}}",
+ "text": "{{Content}}"
+ }
+ }
+ ```
+
+ 7. Click "Select Action" > "Send Feishu Message", check "Group Message", then click the input box below, click "Groups I Manage" (if no group, you can create one in Feishu app)
+
+ 8. Message title fill "TrendRadar Trending Monitor"
+
+ 9. Most critical part, click + button, select "Webhook Trigger", then arrange as shown in image
+
+ 
+
+ 10. After configuration, put Webhook address from step 5 into GitHub Secrets `FEISHU_WEBHOOK_URL`
@@ -1399,7 +1435,31 @@ docker exec -it trend-radar ls -la /app/config/
## 🤖 AI Analysis Deployment
-TrendRadar v3.0.0 added **MCP (Model Context Protocol)** based AI analysis feature, allowing natural language conversations with news data for deep analysis. Best prerequisite for using **AI features** is running this project for at least one day (accumulate news data).
+TrendRadar v3.0.0 added **MCP (Model Context Protocol)** based AI analysis feature, allowing natural language conversations with news data for deep analysis.
+
+
+### ⚠️ Important Notice Before Use
+
+
+**Critical: AI features require local news data support**
+
+AI analysis **does not** query real-time online data directly, but analyzes **locally accumulated news data** (stored in the `output` folder)
+
+
+#### Usage Instructions:
+
+1. **Built-in Test Data**: The `output` directory includes news data from **November 1-15, 2025** by default for quick feature testing
+
+2. **Query Limitations**:
+ - ✅ Only query data within available date range (Nov 1-15)
+ - ❌ Cannot query real-time news or future dates
+
+3. **Getting Latest Data**:
+ - Test data is for quick experience only, **recommend deploying the project yourself** to get real-time data
+ - Follow [Quick Start](#-quick-start) to deploy and run the project
+ - After accumulating news data for at least 1 day, you can query the latest trending topics
+
+---
### 1. Quick Deployment
@@ -1528,7 +1588,189 @@ Create `.cursor/mcp.json`:
-(Additional client configs including VSCode/Cline/Continue, Claude Code CLI, MCP Inspector, and others available in Chinese version)
+
+👉 Click to expand: VSCode (Cline/Continue)
+
+#### Cline Configuration
+
+Add in Cline's MCP settings:
+
+**HTTP Mode**:
+```json
+{
+ "trendradar": {
+ "url": "http://localhost:3333/mcp",
+ "type": "streamableHttp",
+ "autoApprove": [],
+ "disabled": false
+ }
+}
+```
+
+**STDIO Mode** (Recommended):
+```json
+{
+ "trendradar": {
+ "command": "uv",
+ "args": [
+ "--directory",
+ "/path/to/TrendRadar",
+ "run",
+ "python",
+ "-m",
+ "mcp_server.server"
+ ],
+ "type": "stdio",
+ "disabled": false
+ }
+}
+```
+
+#### Continue Configuration
+
+Edit `~/.continue/config.json`:
+```json
+{
+ "experimental": {
+ "modelContextProtocolServers": [
+ {
+ "transport": {
+ "type": "stdio",
+ "command": "uv",
+ "args": [
+ "--directory",
+ "/path/to/TrendRadar",
+ "run",
+ "python",
+ "-m",
+ "mcp_server.server"
+ ]
+ }
+ }
+ ]
+ }
+}
+```
+
+**Usage Examples**:
+```
+Analyze recent 7 days "Tesla" popularity trend
+Generate today's trending summary report
+Search "Bitcoin" related news and analyze sentiment
+```
+
+
+
+
+👉 Click to expand: Claude Code CLI
+
+#### HTTP Mode Configuration
+
+```bash
+# 1. Start HTTP service
+# Windows: start-http.bat
+# Mac/Linux: ./start-http.sh
+
+# 2. Add MCP server
+claude mcp add --transport http trendradar http://localhost:3333/mcp
+
+# 3. Verify connection (ensure service started)
+claude mcp list
+```
+
+#### Usage Examples
+
+```bash
+# Query news
+claude "Search today's Zhihu trending news, top 10"
+
+# Trend analysis
+claude "Analyze 'artificial intelligence' topic popularity trend for the past week"
+
+# Data comparison
+claude "Compare Zhihu and Weibo platform attention on 'Bitcoin'"
+```
+
+
+
+
+👉 Click to expand: MCP Inspector (Debug Tool)
+
+
+MCP Inspector is the official debug tool for testing MCP connections:
+
+#### Usage Steps
+
+1. **Start TrendRadar HTTP Service**:
+ ```bash
+ # Windows
+ start-http.bat
+
+ # Mac/Linux
+ ./start-http.sh
+ ```
+
+2. **Start MCP Inspector**:
+ ```bash
+ npx @modelcontextprotocol/inspector
+ ```
+
+3. **Connect in Browser**:
+ - Visit: `http://localhost:3333/mcp`
+ - Test "Ping Server" function to verify connection
+ - Check "List Tools" returns 13 tools:
+ - Basic Query: get_latest_news, get_news_by_date, get_trending_topics
+ - Smart Search: search_news, search_related_news_history
+ - Advanced Analysis: analyze_topic_trend, analyze_data_insights, analyze_sentiment, find_similar_news, generate_summary_report
+ - System Management: get_current_config, get_system_status, trigger_crawl
+
+
+
+
+👉 Click to expand: Other MCP-Compatible Clients
+
+
+Any client supporting Model Context Protocol can connect to TrendRadar:
+
+#### HTTP Mode
+
+**Service Address**: `http://localhost:3333/mcp`
+
+**Basic Config Template**:
+```json
+{
+ "name": "trendradar",
+ "url": "http://localhost:3333/mcp",
+ "type": "http",
+ "description": "News Trending Aggregation Analysis"
+}
+```
+
+#### STDIO Mode (Recommended)
+
+**Basic Config Template**:
+```json
+{
+ "name": "trendradar",
+ "command": "uv",
+ "args": [
+ "--directory",
+ "/path/to/TrendRadar",
+ "run",
+ "python",
+ "-m",
+ "mcp_server.server"
+ ],
+ "type": "stdio"
+}
+```
+
+**Notes**:
+- Replace `/path/to/TrendRadar` with actual project path
+- Windows paths use backslash escape: `C:\\Users\\...`
+- Ensure project dependencies installed (ran setup script)
+
+
## ☕ FAQ & Support
@@ -1541,28 +1783,13 @@ Create `.cursor/mcp.json`:
👉 Click to expand: Author's Note
-Thanks for all support! Due to sponsor support, the **one-yuan donation** QR code has been removed.
+Thanks for all support! Due to 302.AI sponsorship, my personal **one-yuan donation** QR code has been removed.
Previous **one-yuan supporters** are listed in the **Acknowledgments** section at the top.
This project's development and maintenance require significant time, effort, and costs (including AI model fees). With sponsorship support, I can maintain it more confidently.
-Currently, major AI model prices are relatively affordable. If you don't have a suitable model yet, clicking **302.AI** below also supports the developer:
-
-
-
-
-
-
+
+---
+
### Common Questions
diff --git a/readme.md b/readme.md
index 46ee792..3593a27 100644
--- a/readme.md
+++ b/readme.md
@@ -46,7 +46,7 @@
| [🎯 核心功能](#-核心功能) | [🚀 快速开始](#-快速开始) | [🐳 Docker部署](#-docker-部署) | [🤖 AI分析专区](#-ai-智能分析部署) |
|:---:|:---:|:---:|:---:|
| [📝 更新日志](#-更新日志) | [🔌 MCP客户端](#-mcp-客户端) | [❓ 答疑与公益](#问题答疑与公益捐助) | [⭐ 项目相关](#项目相关) |
-| [🔧 自定义监控平台](#自定义监控平台) | [📝 frequency_words.txt 配置](#frequencywordstxt-配置教程) | | |
+| [🔧 自定义监控平台](#自定义监控平台) | [📝 推送关键词配置](#frequencywordstxt-配置教程) | [🪄 赞助商](#-赞助商) | |
@@ -517,7 +517,11 @@ weight:
- 跨平台数据对比（活跃度统计、关键词共现）
- 智能摘要生成、相似新闻查找、历史关联检索
-> 告别手动翻阅数据文件，AI 助手帮你秒懂新闻背后的故事
+> **💡 使用提示**：AI 功能需要本地新闻数据支持
+> - 项目自带 **11月1-15日** 测试数据，可立即体验
+> - 建议自行部署运行项目，获取更实时的数据
+>
+> 详见 [AI 智能分析部署](#-ai-智能分析部署)
### **零技术门槛部署**
@@ -1472,7 +1476,31 @@ docker exec -it trend-radar ls -la /app/config/
## 🤖 AI 智能分析部署
-TrendRadar v3.0.0 新增了基于 **MCP (Model Context Protocol)** 的 AI 分析功能，让你可以通过自然语言与新闻数据对话，进行深度分析。使用 **AI 功能** 的最佳前提是已使用本项目至少运行一天(积累新闻数据)
+TrendRadar v3.0.0 新增了基于 **MCP (Model Context Protocol)** 的 AI 分析功能，让你可以通过自然语言与新闻数据对话，进行深度分析。
+
+
+### ⚠️ 使用前必读
+
+
+**重要提示：AI 功能需要本地新闻数据支持**
+
+AI 分析功能**不是**直接查询网络实时数据，而是分析你**本地已积累的新闻数据**（存储在 `output` 文件夹中）
+
+
+#### 使用说明：
+
+1. **项目自带测试数据**：`output` 目录默认包含 **2025年11月1日～11月15日** 的新闻数据，可用于快速体验 AI 功能
+
+2. **查询限制**：
+ - ✅ 只能查询已有日期范围内的数据（11月1-15日）
+ - ❌ 无法查询实时新闻或未来日期
+
+3. **获取最新数据**：
+ - 测试数据仅供快速体验，**建议自行部署项目**获取实时数据
+ - 按照 [快速开始](#-快速开始) 部署运行项目
+ - 等待至少 1 天积累新闻数据后，即可查询最新热点
+
+---
### 1. 快速部署
@@ -1790,35 +1818,17 @@ MCP Inspector 是官方调试工具，用于测试 MCP 连接：
> 如果你想支持本项目，可通过微信搜索**腾讯公益**，对里面的**助学计划**随心捐助~
>
-> 我还在为信息过载而焦虑，他们却在信息荒漠中挣扎，连学习的机会都没有，所以他们比我更需要支持。
+> 我还在为信息过载而焦虑，而他们却在信息荒漠中挣扎，他们比我更需要支持。
👉 点击展开：作者有话说
-感谢各位支持！因获得赞助商赞助，现已移除**一元点赞**打赏码。
+感谢各位支持！因获得赞助商的赞助，现已移除我个人的**一元点赞**打赏码。
之前参与**一元点赞**的朋友已收录至顶部**致谢名单**。
本项目开发和维护投入了大量时间、精力和成本（含 AI 模型费用），有了赞助支持后可以更安心维护。
-
-目前大厂模型价格已相对亲民，如果你手上暂无合适的模型，点击下方**302.AI**也是对开发者的支持：
-
-
-
-
-
-
- **GitHub Issues**：适合针对性强的解答。提问时请提供完整信息（截图、错误日志、系统环境等）。
@@ -1833,18 +1843,59 @@ MCP Inspector 是官方调试工具，用于测试 MCP 连接：
-## 🪄赞助商
-
-> 302.AI 是一个按用量付费的企业级 AI 资源平台
-> 提供市场上最新、最全面的 **AI模型** 和 **API**，以及多种开箱即用的在线 AI 应用。
+## 🪄 赞助商
+> **302.AI** 是按用量付费的企业级 AI 资源平台
+> 提供市场上最新、最全面的 **AI 模型**和 **API**，以及多种开箱即用的在线 AI 应用
+### 💰 302.AI 新用户福利
+
+> 领取的 1 美元可用于调用各种 AI 大模型（如 Claude、GPT 等）
+> 本项目 AI 分析功能需配置大模型使用，配置教程详见 [AI智能分析部署](#-ai-智能分析部署)
+
+[](https://share.302.ai/mEOUzG)
+
+
+
+
+
+---
+
### 常见问题
-
+
+ 
-
+
+