CLI
- python
0
GitHub Stars
python
Language
7 months ago
First Indexed
3 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"mcp-mirror-plurigrid_juvix-mcp-server": {
"command": "uv",
"args": [
"--directory",
"<path>/cli-mcp-server",
"run",
"cli-mcp-server"
],
"env": {
"ALLOWED_DIR": "</your/desired/dir>",
"ALLOWED_FLAGS": "-l,-a,--help,--version",
"COMMAND_TIMEOUT": "30",
"ALLOWED_COMMANDS": "ls,cat,pwd,echo",
"MAX_COMMAND_LENGTH": "1024"
}
}
}
}You can securely run controlled command-line operations through a dedicated MCP server. It enforces strict command and flag whitelisting, path validation, and execution controls so you can provide CLI access to large language model workflows without compromising security or system integrity.
How to use
Use an MCP client to connect to the CLI MCP Server and send whitelisted commands for execution. You will specify the command to run, and the server will validate it against the allowed commands and flags, ensure the working directory is safe, and enforce execution timeouts. You can request outputs, inspect results, or handle errors through the MCP client interface. The server is designed to prevent shell operator injection, enforce path restrictions, and report detailed security and execution information when something goes wrong.
How to install
Prerequisites you need before installing:
Install a Python 3.10+ runtime and ensure you can install MCP protocol libraries in your environment.
Install the CLI MCP Server for Claude Desktop through the package manager you use, ensuring you select the client side integration for Claude.
npx @smithery/cli install cli-mcp-server --client claude
Additional sections
Configuration and security details are provided below to help you set up, run, and manage the CLI MCP Server in a secure, predictable way.
Available tools
run_command
Executes whitelisted CLI commands within allowed directories with security checks including shell operator blocking and path validation.
show_security_rules
Displays current security configuration and restrictions such as working directory, allowed commands, allowed flags, and timeout/length limits.