A secure Model Context Protocol (MCP) server implementation for executing controlled command-line operations with comprehensive security features.
A secure Model Context Protocol (MCP) server implementation for executing controlled command-line operations with comprehensive security features. That is what the cli mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
This MCP server enables secure command-line execution with robust security measures including command whitelisting, path validation, and execution controls. Perfect for providing controlled CLI access to LLM applications while maintaining security.
Installation goes through your MCP client rather than a global install: point it at @smithery/cli on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
The server publishes 4 tools. What each one is for:
run_command — Executes whitelisted CLI commands within allowed directoriesshow_security_rules — Displays current security configuration and restrictions, including: - Working directory - Allowed commands - Allowed flags - Security limits (maxPrerequisites — The Prerequisites tool exposed by this serverDebugging — Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the [MCPConfiguration is passed through the environment: ALLOWED_DIR, ALLOWED_COMMANDS, ALLOWED_FLAGS, MAX_COMMAND_LENGTH, COMMAND_TIMEOUT, ALLOW_SHELL_OPERATORS, YOUR_PYPI_API_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of file and storage access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Cli's toolset — run_command, show_security_rules, Prerequisites and 1 more — is a fair guide to whether it matches your workflow. It is maintained by MladenSU; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| run_command | Executes whitelisted CLI commands within allowed directories. |
| show_security_rules | Displays current security configuration and restrictions, including: - Working directory - Allowed commands - Allowed flags - Security limits (max command length and timeout) |
| Prerequisites | The Prerequisites tool exposed by this server. |
| Debugging | Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector). |
> Published Servers Configuration
```json
{
"mcpServers": {
"cli-mcp-server": {
"command": "uvx",
"args": [
"cli-mcp-server"
],
"env": {
"ALLOWED_DIR": "</your/desired/dir>",
"ALLOWED_COMMANDS": "ls,cat,pwd,echo",
"ALLOWED_FLAGS": "-l,-a,--help,--version",
"MAX_COMMAND_LENGTH": "1024",
"COMMAND_TIMEOUT": "30",
"ALLOW_SHELL_OPERATORS": "false"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| ALLOWED_DIR | Filesystem location the server is allowed to use. | Optional |
| ALLOWED_COMMANDS | Configuration value read at startup. | Optional |
| ALLOWED_FLAGS | Configuration value read at startup. | Optional |
| MAX_COMMAND_LENGTH | Configuration value read at startup. | Optional |
| COMMAND_TIMEOUT | Configuration value read at startup. | Optional |
| ALLOW_SHELL_OPERATORS | Configuration value read at startup. | Optional |
| YOUR_PYPI_API_TOKEN | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.