Quick MCP Shell
Amazon Quick 的执行环境是一个隔离的sandbox,无法调用本地命令,需要借助MCP才能够在本机执行 shell 命令和 运行Python 脚本。 例如:本地安装了 lark-cli 操作飞书,但是Quick无法直接使用 lark-cli 命令,可以通过该MCP执行 lark-cli 命令。
安装 uv
Amazon Quick 使用 uvx 启动本工具。
- Windows(PowerShell):
winget install --id=astral-sh.uv -e - macOS:
brew install uv - Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
执行 uvx --version 确认 uvx 已成功安装。
配置 Amazon Quick
打开 Settings → Capabilities → MCP Servers,编辑配置文件(通常是 ~/.aws/amazonq/mcp.json),在 mcpServers 下添加一个服务条目(下例命名为 shell):
{
"mcpServers": {
"execute-cmd": {
"command": "uvx",
"args": ["--from", "quick-mcp-shell==0.4.2", "quick-mcp-shell"]
}
}
}
若已有其他 MCP 服务,把 "shell": { ... } 这一条目并入现有的 mcpServers 对象即可。
工具
配置完成后,Amazon Quick 会自动获得下面两个工具,并在需要时自行调用;你只需用自然语言向 Quick 描述需求,无需手动调用。
run_command:执行 shell 命令。Windows 上通过cmd.exe执行(不是 PowerShell),macOS/Linux 上通过/bin/sh执行。run_python_script:执行 Python 脚本。使用本工具自带的隔离解释器,项目里安装的第三方包(如 pandas)不可用;需要项目依赖时让 Quick 改用run_command。
两个工具都支持可选的 cwd 和 timeout 参数,由 Quick 在调用时传入:不传 cwd 时使用当前用户的主目录,相对路径也相对主目录解析,传入绝对路径时可指定任意存在的目录;timeout 默认 30 秒、最大 60 秒,超时会终止整个进程树。
可选环境变量:
| 变量 | 默认值 | 作用 |
|---|---|---|
MCP_SHELL_MAX_TIMEOUT_SECONDS |
60 |
单次调用允许的最大超时秒数。 |
MCP_SHELL_MAX_OUTPUT_CHARS |
100000 |
返回结果的最大字符数,超出时保留首尾两段。 |
检查启动环境:
uvx --from quick-mcp-shell==0.4.2 quick-mcp-shell doctor
安全边界
本工具不限制命令访问的目录。命令可以切换目录或使用绝对路径;若需要真正的访问隔离,请使用受限系统账户、容器或操作系统权限控制。
Metadata
Release files for quick-mcp-shell 0.4.2
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 | Actions |
|---|---|---|---|---|
| quick_mcp_shell-0.4.2.tar.gz | 8.2 kB | Without provenance | Details for quick_mcp_shell-0.4.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| quick_mcp_shell-0.4.2-py3-none-any.whl | Python 3 | none | any | Details for quick_mcp_shell-0.4.2-py3-none-any.whl |
Total release size: 16.6 kB
Release files / quick_mcp_shell-0.4.2.tar.gz
| Download URL | quick_mcp_shell-0.4.2.tar.gz |
|---|---|
| Size | 8.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
35c123130d1a6e0b3455941c7984a6bd1c2ae2ff64c71ffd22c926a3670be8ce
|
|
BLAKE2b-256 checksum How to use checksums |
1ceaad1347f8e3afc7f224f1546620a6d3eecd7f41477fa25995ca972fd89f62
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.12.1 {"installer":{"name":"uv","version":"0.12.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / quick_mcp_shell-0.4.2-py3-none-any.whl
| Download URL | quick_mcp_shell-0.4.2-py3-none-any.whl |
|---|---|
| Size | 8.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
efa62b6f90f6b48d72b16e9f1c78046d5bb82078f146b40f40a5bcebe8cfff7b
|
|
BLAKE2b-256 checksum How to use checksums |
26b6c1fc1a1d864b074554862b8ed60b7c6d9a018cb94a32fbf3a18f88110fc0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.12.1 {"installer":{"name":"uv","version":"0.12.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for quick-mcp-shell 0.4.2
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.
To learn more about protecting yourself from malicious actors, visit our package security documentation.