Unified CLI and Python client for Openboost TikTok, Patent, and Amazon MCP servers.
Project description
openboost-cli
统一 Openboost MCP 命令行工具,包含 TikTok、Patent、Amazon 三套 MCP 的交互式菜单、快捷命令、通用调用和 Python 客户端。
终端命令为 openboost(包名 openboost-cli)。
完整使用说明见 使用文档.md。
安装
从源码开发安装
cd "/path/to/openboost-cli"
python3.12 -m venv .venv
source .venv/bin/activate
pip install --upgrade pip
pip install -e ".[dev]"
从离线安装包安装(wheel / 源码包)
仓库内每次执行 python -m build 后,安装包位于 dist/:
| 文件 | 说明 |
|---|---|
openboost_cli-<版本>-py3-none-any.whl |
推荐:纯 Python,任意平台 Python 3.10+ 可用 |
openboost_cli-<版本>.tar.gz |
源码分发包,pip 会本地构建后安装 |
在任意虚拟环境或全局环境中(需 Python ≥ 3.10,且能访问 PyPI 以下载依赖 httpx、mcp、rich、typer):
pip install --upgrade pip
pip install "/path/to/openboost-cli/dist/openboost_cli-1.0.1-py3-none-any.whl"
若机器完全离线,需事先在同一 Python 版本下准备好依赖的 wheel,或使用带依赖缓存的 pip download,再 pip install --no-index 指向本地目录;此处与常规 Python 离线安装流程相同。
安装后命令为:
openboost --help
自行打包安装包
在 openboost-cli 项目根目录:
pip install build
python -m build
产物写入 dist/(*.whl 与 *.tar.gz),可将整个 dist 目录或单个文件拷贝给其他环境安装。
配置密钥
三套 MCP 共用同一个密钥时:
openboost config set --secret-key "你的密钥"
也可以只配置某一个 MCP:
openboost config set --mcp patent --secret-key "你的密钥"
openboost config set --mcp amazon --base-url "http://mcp.microdata-inc.com/mcp-servers/proboost-amazon-mcp"
环境变量也支持:
export OPENBOOST_SECRET_KEY="通用密钥"
export OPENBOOST_TIKTOK_SECRET_KEY="TikTok 专用密钥"
export OPENBOOST_PATENT_SECRET_KEY="Patent 专用密钥"
export OPENBOOST_AMAZON_SECRET_KEY="Amazon 专用密钥"
通用命令
openboost # 交互式菜单
openboost list # 列出全部 55 个工具
openboost docs patent patent_query_search
openboost call tiktok tt_video_content \
--set countryRegion=美国 \
--set videoId=7587942790298979614
openboost call patent patent_query_count \
--set query_text="TACD: virtual reality"
openboost call amazon amz_product_selection \
--set webSiteId=1 \
--set pages=1 \
--set pagesSize=10
快捷命令示例
TikTok:
openboost tiktok commodity category-tree
openboost tiktok video content 7587942790298979614 --country 美国
openboost tiktok shop list --data-period last30d --country 美国
Patent:
openboost patent search count "TACD: virtual reality"
openboost patent search query "TACD: virtual reality" --limit 10
openboost patent detail bibliography --patent-number US11205304B2
openboost patent image-search single "https://example.com/image.jpg" --model 1 --patent-type D
Amazon:
openboost amazon product selection --site 1 --pages 1 --pages-size 10
openboost amazon product sku B0EXAMPLE --site 1
openboost amazon hot cat-tree --site 1 --rank-type "Best Seller"
复杂筛选条件可追加 key=value:
openboost amazon product selection --site 1 minPrice=10 maxPrice=30 sortField=sku_sales_last_30d sortOrder=desc
Python 客户端
from openboost_cli import Openboost
pb = Openboost()
content = pb.tiktok.tt_video_content(countryRegion="美国", videoId="7587942790298979614")
count = pb.patent.patent_query_count(query_text="TACD: virtual reality")
items = pb.amazon.amz_product_selection(webSiteId="1", pages=1, pagesSize=10)
测试
python -m pytest
openboost --help
openboost list
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 openboost_cli-1.0.1.tar.gz.
File metadata
- Download URL: openboost_cli-1.0.1.tar.gz
- Upload date:
- Size: 37.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.6.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9827d4b504d2eb531ff5e095725647ab011612fc5ea909437fe2fc074d86d2ad
|
|
| MD5 |
d61a59637a6c6411cfeb47e7562c7108
|
|
| BLAKE2b-256 |
e3d81b5dda571f15a098d68b75b6b259ca9aef17a641b4c76f5aaa875103d834
|
File details
Details for the file openboost_cli-1.0.1-py3-none-any.whl.
File metadata
- Download URL: openboost_cli-1.0.1-py3-none-any.whl
- Upload date:
- Size: 67.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.6.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ef74009ef3d5701558dcff29dfdfab4d834a602e1ebe4abe3d606f9afa69296b
|
|
| MD5 |
e2841e05748482a0eb60c7a7069db793
|
|
| BLAKE2b-256 |
b614ff1137571f99fc76f91e43dcf73279faf1b703c77769e792fb195450751e
|