Windows CLISAFE
Model Context Protocol server for secure command-line interactions on Windows systems
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[!CAUTION] PROJECT DEPRECATED - No longer maintained. Use https://github.com/wonderwhy-er/DesktopCommanderMCP instead for similar functionality.
[](https://www.npmjs.com/package/@simonb97/server-win-cli) [](https://www.npmjs.com/package/@simonb97/server-win-cli?activeTab=versions) [](https://smithery.ai/server/@simonb97/server-win-cli)
MCP server for secure command-line interactions on Windows systems, enabling controlled access to PowerShell, CMD, Git Bash shells, and remote systems via SSH. It allows MCP clients (like Claude Desktop) to perform operations on your system, similar to Open Interpreter.
[!IMPORTANT] This MCP server provides direct access to your system's command line interface and remote systems via SSH. When enabled, it grants access to your files, environment variables, command execution capabilities, and remote server management. - Review and restrict allowed paths and SSH connections - Enable directory restrictions - Configure command blocks - Consider security implications See Configuration for more details.
- Features
- Usage with Claude Desktop
- Configuration
- Configuration Locations
- Default Configuration
- Configuration Settings
- Security Settings
- Shell Configuration
- SSH Configuration
- API
- Tools
- Resources
- [Security Considerations
59df4ad4e79bOBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add server-win-cli -- npx -y @simonb97/[email protected]
{
"mcpServers": {
"server-win-cli": {
"command": "npx",
"args": [
"-y",
"@simonb97/[email protected]"
]
}
}
}Exposed tools (9)
4 read · 4 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
create_ssh_connection | write | Create a new SSH connection |
delete_ssh_connection | destructive | Delete an existing SSH connection |
execute_command | write | Execute a command in the specified shell (powershell, cmd, or gitbash) Example usage (PowerShell): \ |
get_command_history | read | Get the history of executed commands Example usage: \ |
get_current_directory | read | Get the current working directory |
read_ssh_connections | read | Read all SSH connections |
ssh_disconnect | read | Disconnect from an SSH server Example usage: \ |
ssh_execute | write | Execute a command on a remote host via SSH Example usage: \ |
update_ssh_connection | write | Update an existing SSH connection |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (4)
delete_ssh_connection
@types/ssh2, ssh2, yargs, zod, @jest/globals, @types/jest, @types/node, @types/yargs
> This MCP server provides direct access to your system's command line interface and remote systems via SSH. When enabled, it grants access to your files, environment variables, command execution capa
- **Environment access**: Commands may have access to environment variables, which could contain sensitive information
Gates applied: no_behavioural_pass.
59df4ad4e79bfull audit observations/trust-audit/mcp-server/simonb97__windows-cli.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | 59df4ad4e79b | SAFE | B | 89 | first audit |
Questions
What is the Windows CLI MCP server?
Model Context Protocol server for secure command-line interactions on Windows systems
What tools does Windows CLI expose?
9 in total: 4 read-only, 4 that write, and 1 that can delete or overwrite (delete_ssh_connection). Every one is listed on this page with its risk.
Is Windows CLI safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Windows CLI need?
No credential environment variables were found in its source, so it appears to need none.
How does Windows CLI run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @simonb97/server-win-cli at 0.2.1.
How current is this page?
The grade is for one exact copy of the source (59df4ad4e79b), read on 2026-10-06. The repository is watched and re-audited when it changes.