What shells are supported?
PowerShell, Command Prompt (CMD), and Git Bash are supported. Each can be enabled or disabled in the configuration.
@MCP-Mirror
Basic information
Mirror of
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"SimonB97_win-cli-mcp-server": {
"command": "npx",
"args": [
"@simonb97/server-win-cli",
"--init-config",
"./config.json"
]
}
}
}Execute a command in the specified shell
Get the history of executed commands
Execute a command on a remote system via SSH
Disconnect from an SSH server
Windows CLI MCP Server is an 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.
Add the server to your claude_desktop_config.json using npx -y @simonb97/server-win-cli. Optionally specify a config file with the --config flag. Create a default config by copying config.json.example or running npx @simonb97/server-win-cli --init-config ./config.json.
PowerShell, Command Prompt (CMD), and Git Bash are supported. Each can be enabled or disabled in the configuration.
Blocked commands and arguments are defined in the `security` section of the config file. Blocked commands apply to both direct use and full paths, case-insensitively.
Yes, SSH is supported but disabled by default. You can enable it and configure connection profiles (password or key authentication) in the `ssh` config section.
The server looks for config in order: path specified by `--config` flag, `./config.json`, or `~/.win-cli-mcp/config.json`.
Default settings include command length limit (2000 chars), blocked dangerous commands (rm, del, format, etc.), restricted working directory to user's home and current directory, command logging, and injection protection enabled.

MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R
Comments