S
sandbaseai/cli
CLI and local server for many clients and model APIs, with rollback
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
远端端点（Claude Desktop / Cursor / Windsurf 共用 mcpServers）
{
"mcpServers": {
"sandbaseai-cli": {
"url": "https://sandbase.ai/v1/mcp"
}
}
}把这段粘进 Claude Desktop / Cursor 的 mcpServers 配置即可。端点来自公开证据，我们没有替你安装或托管它。 官方 Registry 记录：这个端点列了【必填】请求头 Authorization（Bearer credential issued by the SandBase browser sign-in flow）。用它要带上你自己的凭据。
VS Code（.vscode/mcp.json —— 键名是 servers，远程要 type: http）
{
"servers": {
"sandbaseai-cli": {
"type": "http",
"url": "https://sandbase.ai/v1/mcp"
}
}
}VS Code 的配置文件和另外三家不同：顶层键是 <code>servers</code>，远程端点还要写 <code>"type": "http"</code>。复制到 .vscode/mcp.json。
Claude Code（命令行）
claude mcp add --transport http sandbaseai-cli https://sandbase.ai/v1/mcp
Claude Code 不收 JSON 文件，用这条命令直接加。
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"sandbaseai-cli": {
"command": "npx",
"args": ["-y", "@sandbaseai/cli@latest"]
}
}
}解析自我们于 2026-11-04 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"sandbaseai-cli": {
"command": "npx",
"args": ["-y", "@sandbaseai/cli@latest"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio sandbaseai-cli -- npx -y @sandbaseai/cli@latest
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- 来源明细
- 收录自 abordage/awesome-mcp 榜单（我们从中收集的条目之一） · 条目类型：MCP 服务
- 收录与活跃
- 收录于 2026-11-05 · 最近见到 2026-11-14 · 共见到 10 次 · 被 10 个来源列出
- 评分构成
- 综合分 1,003 · 10 个来源 · mcp
- 安装
npx -y @sandbaseai/cli@latest
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
npx -y @sandbaseai/cli@latest。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: MCP 服务。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
我们收录于 2026-11-05；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。
@sandbaseai/cli
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
Give your AI agent superpowers. One line. 2,000+ AI models and APIs. 100 free data API calls a day, then pay per call from one balance.
English | 中文 | 日本語 | 한국어 | Español | Français | Deutsch | Português
Your AI coding assistant is smart, but it's trapped in a box. It can't search the web, check social media, generate images, or access real-time data — unless you wire up each API yourself.
SandBase changes that. One command connects your agent to 2,000+ AI models and APIs through the Model Context Protocol. No API keys to manage. No configuration headaches.
Building directly over HTTP instead of MCP? Start with the SandBase API quickstart
or compare the unified LLM, image, and video API
with specialized model gateways.
## Setup
Paste this into your agent and let it do the rest:
set up https://www.sandbase.ai/SKILL.md
It reads the SandBase Skill, runs connect itself, and asks you to approve one browser sign-in. Prefer to drive it yourself:
sh
npx -y @sandbaseai/cli@latest connect
Or install the official Homebrew formula on macOS or Linux:
sh
brew install sandbaseai/tap/sandbaseai-cli
sandbase connect
See the Homebrew launch announcement and macOS/Linux CI evidence.
Approve the browser authorization once; each supported client can then discover,
inspect, and run available SandBase models and APIs through the local MCP bridge.
Start a new session afterwards so the sandbase tools load.
Every GitHub release publishes its own SHA-256 next to the tarball, so you can pin
and verify an exact build instead of tracking latest:
sh
V=$(npm view @sandbaseai/cli version)
curl -fL -O "https://github.com/sandbaseai/cli/releases/download/v$V/sandbaseai-cli-$V.tgz"
shasum -a 256 "sandbaseai-cli-$V.tgz" # compare against the checksum on the release page
npx -y "./sandbaseai-cli-$V.tgz" connect
Want to inspect compatibility before signing in or changing configuration? The
client catalog is a read-only command — it writes nothing and needs no account:
sh
npx -y @sandbaseai/cli@latest catalog --json
A no-write catalog audit and a bounded doctor check against an empty isolated profile.
Homebrew users can run the same read-only check with sandbase catalog --json.
## What It Costs
| | Price |
| Data APIs — search, social, scraping, e-commerce, finance | 100 free calls/day per organization, then paid per call (price shown by sandbase inspect) |
| Discovery, inspection, run status, balance, file upload | Free |
| Models — LLM, image, video, audio | Paid per call or per million tokens |
sandbase inspect always shows the current price before you run anything;
data APIs covered by the daily allowance also show pricing.freequota. The 100
free calls are shared across eligible data APIs and reset at 00:00 UTC; after
that, calls are billed per call. sandbase balance --json shows today's remaining free
calls as freeapiquota. Prices can change, so trust the live response over
any example in this file.
Visit the official SandBase CLI project page for a compact overview.
For a security-focused walkthrough of client detection, MCP tools, and rollback,
read the 25-client SandBase CLI setup guide.
AI agents and automated installers can use the concise
llms-install.md instructions.
English | 中文 | 日本語 | 한국어 | Español | Français | Deutsch | Português
Your AI coding assistant is smart, but it's trapped in a box. It can't search the web, check social media, generate images, or access real-time data — unless you wire up each API yourself.
SandBase changes that. One command connects your agent to 2,000+ AI models and APIs through the Model Context Protocol. No API keys to manage. No configuration headaches.
Building directly over HTTP instead of MCP? Start with the SandBase API quickstart
or compare the unified LLM, image, and video API
with specialized model gateways.
## Setup
Paste this into your agent and let it do the rest:
set up https://www.sandbase.ai/SKILL.md
It reads the SandBase Skill, runs connect itself, and asks you to approve one browser sign-in. Prefer to drive it yourself:
sh
npx -y @sandbaseai/cli@latest connect
Or install the official Homebrew formula on macOS or Linux:
sh
brew install sandbaseai/tap/sandbaseai-cli
sandbase connect
See the Homebrew launch announcement and macOS/Linux CI evidence.
Approve the browser authorization once; each supported client can then discover,
inspect, and run available SandBase models and APIs through the local MCP bridge.
Start a new session afterwards so the sandbase tools load.
Every GitHub release publishes its own SHA-256 next to the tarball, so you can pin
and verify an exact build instead of tracking latest:
sh
V=$(npm view @sandbaseai/cli version)
curl -fL -O "https://github.com/sandbaseai/cli/releases/download/v$V/sandbaseai-cli-$V.tgz"
shasum -a 256 "sandbaseai-cli-$V.tgz" # compare against the checksum on the release page
npx -y "./sandbaseai-cli-$V.tgz" connect
Want to inspect compatibility before signing in or changing configuration? The
client catalog is a read-only command — it writes nothing and needs no account:
sh
npx -y @sandbaseai/cli@latest catalog --json
A no-write catalog audit and a bounded doctor check against an empty isolated profile.
Homebrew users can run the same read-only check with sandbase catalog --json.
## What It Costs
| | Price |
| Data APIs — search, social, scraping, e-commerce, finance | 100 free calls/day per organization, then paid per call (price shown by sandbase inspect) |
| Discovery, inspection, run status, balance, file upload | Free |
| Models — LLM, image, video, audio | Paid per call or per million tokens |
sandbase inspect always shows the current price before you run anything;
data APIs covered by the daily allowance also show pricing.freequota. The 100
free calls are shared across eligible data APIs and reset at 00:00 UTC; after
that, calls are billed per call. sandbase balance --json shows today's remaining free
calls as freeapiquota. Prices can change, so trust the live response over
any example in this file.
Visit the official SandBase CLI project page for a compact overview.
For a security-focused walkthrough of client detection, MCP tools, and rollback,
read the 25-client SandBase CLI setup guide.
AI agents and automated installers can use the concise
llms-install.md instructions.
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/sandbaseai-cli/)
- 来源
- awesome · https://github.com/sandbaseai/cli
- 按领域浏览
- MCP 服务
- 收录来源
- 10 个独立来源
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。