🤖 mcp-tech-ai-tracker
科技AI资讯 MCP Server — 模型排行、开源趋势、AI行业速览、每日多源摘要,一个 Server 全搞定。
基于扣子技能 tech-ai-tracker 重写为 MCP Server。
数据源:GitHub Search API + HackerNews Algolia API + arXiv API + HuggingFace API + TianAPI(可选)。
🛠 工具列表
| 工具 | 功能 | 典型场景 |
|---|---|---|
model_rank |
模型排行与技术数据:LLM排行/开源趋势/Benchmark对比 | "LLM下载排行" "AI开源趋势" "模型对比" |
ai_pulse |
AI行业速览:今日热点/本周回顾/热门话题 | "今天AI圈有什么" "本周AI热点" |
tech_digest |
每日多源摘要:新闻+开源+论文+模型一键聚合 | "今天的AI摘要" "科技日报" |
📦 安装
pip install mcp-tech-ai-tracker
或从源码安装:
git clone https://github.com/yourname/mcp-tech-ai-tracker.git
cd mcp-tech-ai-tracker
pip install -e .
⚙️ 配置
可选
TianAPI API 密钥(免费注册即得,用于AI/科技新闻增强):
export TIANAPI_KEY="your_api_key_here"
不设置 TIANAPI_KEY 时,
ai_pulse和tech_digest仍可返回 HackerNews 社区热点和开源数据(跳过新闻部分)。
🚀 使用
命令行
# STDIO 模式 (默认)
mcp-tech-ai-tracker
# 或
python -m mcp_tech_ai_tracker
MCP 客户端配置
在 Claude Desktop / Cherry Studio / ChatBox 等 MCP 客户端中添加:
{
"mcpServers": {
"tech-ai-tracker": {
"command": "mcp-tech-ai-tracker",
"env": {
"TIANAPI_KEY": "your_tianapi_key"
}
}
}
}
开发测试
# 安装 FastMCP CLI
pip install "mcp[cli]"
# 交互式测试
mcp dev src/mcp_tech_ai_tracker/server.py
💡 工具详细说明
model_rank — 模型排行与技术数据
# LLM模型下载排行 (优先HuggingFace,不可用时降级到GitHub)
model_rank(action="llm_rank")
# 指定分类
model_rank(action="llm_rank", category="text-generation")
# 开源AI项目趋势
model_rank(action="trending_repos")
# 指定语言和时间范围
model_rank(action="trending_repos", language="python", time_range="7d")
# Benchmark对比 (需HuggingFace,不可用时降级)
model_rank(action="model_compare")
参数:
action: llm_rank / trending_repos / model_comparecategory: 模型分类过滤(llm_rank/model_compare)language: 编程语言过滤(trending_repos)time_range: 7d / 30d / 365dtop_n: 返回条数,默认10,最大30
ai_pulse — AI行业速览
# 今日AI速览
ai_pulse(action="today")
# 本周科技回顾
ai_pulse(action="weekly", category="tech")
# 热门开源话题
ai_pulse(action="hot", category="opensource")
# 关键词过滤
ai_pulse(action="today", keyword="GPT")
参数:
action: today / weekly / hotcategory: ai / tech / opensourcekeyword: 过滤关键词
数据源:HackerNews(技术社区热点)+ TianAPI(AI/科技/IT新闻,需KEY),30天时效过滤
tech_digest — 每日多源摘要
# 今日完整摘要(新闻+开源+论文+模型)
tech_digest()
# 指定日期
tech_digest(date="2025-05-15")
# 只要论文和模型
tech_digest(include="papers,models")
# 只要新闻
tech_digest(include="news")
参数:
date: 指定日期,YYYY-MM-DD格式,不传则默认今天- `include**: 包含内容类型,逗号分隔: news/repos/papers/models,默认全部
数据源:GitHub+HackerNews+arXiv+HuggingFace+TianAPI,30天时效过滤,约200 tokens精简输出
📋 数据源
| 优先级 | 数据源 | 覆盖 | 限制 |
|---|---|---|---|
| 主力 | GitHub Search API | 开源项目趋势 | 10次/分钟,内置频率控制 |
| 主力 | HackerNews Algolia API | 技术社区热点 | 免费 |
| 主力 | arXiv API | AI论文 | 免费 |
| 增强 | HuggingFace API | 模型排行/Benchmark | 国内可能不可访问,自动降级 |
| 降级 | TianAPI | AI/科技/IT新闻 | 需TIANAPI_KEY |
📋 环境变量
| 变量 | 必需 | 说明 |
|---|---|---|
TIANAPI_KEY |
❌ | 天聚数行API密钥,AI/科技新闻增强用,不设置时跳过新闻部分 |
🔧 降级策略
- HuggingFace 不可用:自动降级到 GitHub AI 项目排行(按Stars排序)
- GitHub API 频率限制:内置请求间隔0.6秒的频率控制
- TianAPI 无 KEY:跳过新闻部分,仅返回 HackerNews 社区数据
- 所有新闻数据:30天时效过滤,过期数据自动移除
📄 License
MIT
Metadata
Release files for mcp-tech-ai-tracker 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| mcp_tech_ai_tracker-0.1.0.tar.gz | 10.5 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| mcp_tech_ai_tracker-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 23.8 kB
Release files / mcp_tech_ai_tracker-0.1.0.tar.gz
| Download URL | mcp_tech_ai_tracker-0.1.0.tar.gz |
|---|---|
| Size | 10.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c6056e604a15df2698857431ef701c436968234908d28ecd7f114791dbf695cc
|
|
BLAKE2b-256 checksum How to use checksums |
82a5d721c4167868e401ff1e32de522b5336daaf6a7726930dc9f9454c1d0fc5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.12
|
Release files / mcp_tech_ai_tracker-0.1.0-py3-none-any.whl
| Download URL | mcp_tech_ai_tracker-0.1.0-py3-none-any.whl |
|---|---|
| Size | 13.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
28a16b38d58f399d6707a4dd2d6993a99150774efbfcb6736af81ce63a27182d
|
|
BLAKE2b-256 checksum How to use checksums |
c11d5c72b0ed40ca150129ce10a7c0cc997d282136ed3c9259e71019e785a02a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.12
|
Security for mcp-tech-ai-tracker 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.