AI Hot Radar MCP Server — 让 Claude/Cursor 实时获取 AI 行业热点新闻,无需启动项目后端
Project description
aihotradar-mcp
让 Claude Desktop、Cursor、Windsurf 等 AI 工具实时获取 AI 行业热点新闻。
无需启动项目后端,独立运行,数据存储于 ~/.aihotradar/data.db。
快速开始
安装
# 使用 uvx(推荐,无需手动安装)
uvx aihotradar-mcp
# 或 pip 安装
pip install aihotradar-mcp
# 启用 AI 深度分析(可选)
pip install "aihotradar-mcp[ai]"
配置 Claude Desktop
编辑 ~/Library/Application Support/Claude/claude_desktop_config.json(macOS)
或 %APPDATA%\Claude\claude_desktop_config.json(Windows):
{
"mcpServers": {
"aihotradar": {
"command": "uvx",
"args": ["aihotradar-mcp"],
"env": {
"AI_API_KEY": "sk-xxx(可选)"
}
}
}
}
配置 Cursor / Windsurf
在项目的 .cursor/mcp.json 或全局 MCP 配置中添加同样的配置。
可用工具
| 工具 | 说明 | 是否需要网络 |
|---|---|---|
search_news |
全文搜索已采集的 AI 新闻 | 否 |
get_trending |
获取热点新闻 | 否 |
trigger_scan |
立即采集并分析最新新闻 | 是 |
add_keyword |
添加监控关键词 | 否 |
list_keywords |
查看关键词及命中统计 | 否 |
get_alerts |
查看关键词命中告警 | 否 |
get_scan_history |
查看历次扫描记录 | 否 |
环境变量(全部可选)
| 变量 | 说明 |
|---|---|
AI_API_KEY |
AI 分析 Key(DeepSeek / OpenAI 兼容) |
AI_BASE_URL |
AI API 地址(默认 https://api.deepseek.com) |
AI_MODEL |
模型名称(默认 deepseek-chat) |
OPENROUTER_API_KEY |
OpenRouter Key(AI_API_KEY 未设置时使用) |
不配置任何 Key 时,使用规则评分,仍可正常采集和搜索新闻。
数据来源(无需任何 API Key)
- OpenAI / Anthropic / Google DeepMind / Hugging Face 官方博客
- TechCrunch AI、MIT Technology Review、The Verge AI、Ars Technica AI
- HackerNews(AI 相关热帖)
- Papers With Code、arXiv cs.AI / cs.LG
- 机器之心、量子位、36氪
- Google News RSS、Bing News 爬虫
许可证
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file aihotradar_mcp-0.1.0.tar.gz.
File metadata
- Download URL: aihotradar_mcp-0.1.0.tar.gz
- Upload date:
- Size: 18.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
dbb39346803c085d23e18ca8d73dce4a031dd402e216e690eb08e7ce5f95e3c3
|
|
| MD5 |
aab6520025671ade39f6431c3a87c4ed
|
|
| BLAKE2b-256 |
4161bf05f285f570711e2a46093006377dbe346fc59692577aca15058e67e5f2
|
File details
Details for the file aihotradar_mcp-0.1.0-py3-none-any.whl.
File metadata
- Download URL: aihotradar_mcp-0.1.0-py3-none-any.whl
- Upload date:
- Size: 23.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fc5b9020cbc3f8db6fe709b33a2af409a0d9582c200401510d946ca006ebb95e
|
|
| MD5 |
29da2134f38cdca4813360715fc9ca51
|
|
| BLAKE2b-256 |
692444f88bf70cfcb9441e10abaa890f16c845e0f732c7f5ce7e46287d4ca70d
|