Skip to main content
Glama
enesjakozh
Faucet94

Super Windows CLI MCP Server

by Faucet94
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Super Windows CLI MCP Server

An enhanced fork of the Windows CLI MCP Server providing unrestricted system access to Windows environments via a command-line interface (MCP).

Based on: win-cli-mcp-server by SimonB97.

⚠️ CRITICAL SECURITY WARNING ⚠️

This server is designed to run with SYSTEM-level privileges on Windows. This grants it complete and unrestricted access to the entire operating system, including all files, processes, and configuration settings.

  • DO NOT install or run this server unless you fully understand the implications of granting SYSTEM-level access.

  • ONLY use this server in highly trusted environments where you have full control over network access.

  • NETWORK SECURITY IS PARAMOUNT: Since application-level restrictions are minimal by design, rely heavily on firewalls, network segmentation, and strict access control lists (ACLs) to protect the machine running this server.

  • REVIEW THE CONFIGURATION CAREFULLY: Pay close attention to allowedPaths, blockedCommands, and other security settings in config.json. A misconfiguration can easily expose your system.

Use this software responsibly and at your own risk. The maintainers assume no liability for misuse or security breaches resulting from its use.

Related MCP server: Windows CLI MCP Server

Features

  • Complete access to Windows shell environments (PowerShell, CMD, Git Bash - configurable).

  • Unrestricted command execution (configurable via config.json).

  • Full file system access (configurable via config.json).

  • SYSTEM-level service installation via NSSM for persistence and auto-recovery.

  • Automatic service recovery features provided by NSSM.

  • Network binding controls (intended, but primarily managed at the network/firewall level).

  • Disabled PowerShell telemetry for enhanced privacy.

  • Process reuse for performance (for shells).

  • Extended timeouts for long-running operations (configurable).

Prerequisites

Before you begin, ensure you have the following installed:

  1. Node.js: Version 18.0.0 or later. Download from nodejs.org. (Includes npm).

  2. NSSM (Non-Sucking Service Manager): Required for reliable service installation. Download the latest version from nssm.cc.

Installation (Using NSSM - Recommended)

This method installs the server as a persistent Windows service that runs with SYSTEM privileges and starts automatically.

  1. Clone or Download:

    • Clone this repository: git clone <repository-url>

    • Or download the source code .zip and extract it to a suitable location (e.g., C:\Servers\SuperWinCLIServer). Avoid user profile folders.

  2. Place NSSM:

    • Download NSSM from nssm.cc.

    • Extract the zip file.

    • Copy the nssm.exe file from the appropriate architecture folder (win32 or win64) into the root directory of this project (the same folder as install-service.ps1).

  3. Install Dependencies & Build:

    • Open a terminal (PowerShell or CMD) in the project's root directory.

    • Run: npm install

    • This command installs necessary Node.js packages and automatically runs npm run build to compile the TypeScript code into the dist folder.

  4. Configure config.json:

    • Copy: Make a copy of config.sample.json and name it config.json in the project's root directory.

    • Edit: Open config.json and carefully review and modify the settings:

      • security.allowedPaths: CRITICAL! Change this from the sample paths to the actual directories the server needs access to. For security, be as specific as possible. Start with the project directory itself if unsure (e.g., "C:\\Servers\\SuperWinCLIServer" - remember double backslashes \\). The service runs as SYSTEM, so paths must be valid for that account.

      • security.blockedCommands / blockedArguments: Review the default lists. Add or remove commands/arguments based on your security policy.

      • shells: Enable/disable shells (PowerShell, CMD, Git Bash) and verify the command path (especially for Git Bash).

      • ssh: Configure if you intend to use the SSH execution feature (disabled by default).

    • Save the config.json file.

  5. Run Installation Script:

    • Open PowerShell as Administrator.

    • Navigate to the project's root directory (cd C:\Servers\SuperWinCLIServer).

    • Execute the installation script: .\install-service.ps1

    • This script uses NSSM to install and configure the MCPServer service to run node.exe dist/index.js as LocalSystem, starting automatically.

  6. Verify Service Status:

    • In the same administrative PowerShell window, run: Get-Service MCPServer

    • The status should be Running. If it's Stopped, check the NSSM logs or Windows Event Viewer (Application and System logs) for errors.

Configuration (config.json) Details

  • security:

    • maxCommandLength: Max characters allowed in a command string.

    • blockedCommands: Array of command names (without extension) to block (case-insensitive).

    • blockedArguments: Array of exact arguments to block (case-insensitive).

    • allowedPaths: Crucial setting. Array of absolute paths. If restrictWorkingDirectory is true, commands can only be executed if their working directory starts with one of these paths. Paths are compared case-insensitively after normalization. Use double backslashes (e.g., "C:\\Tools\\Scripts").

    • restrictWorkingDirectory: Boolean. If true, enforce the allowedPaths check for the working directory. Highly recommended to keep true.

    • logCommands: Boolean. If true, executed commands and their output (truncated) are stored in memory (up to maxHistorySize).

    • maxHistorySize: Max number of commands to keep in the in-memory history.

    • commandTimeout: Seconds before a running command is killed automatically.

    • enableInjectionProtection: Boolean. If true, attempts to block shell operators (&, |, ;, etc. defined per shell) in commands.

  • shells: Configure available local shells (powershell, cmd, gitbash).

    • enabled: Boolean. Allow use of this shell.

    • command: Path to the shell executable.

    • args: Array of default arguments passed to the shell before the user's command.

    • blockedOperators: Array of strings/characters to block within commands for this specific shell (used if enableInjectionProtection is true).

  • ssh: Configure remote command execution via SSH.

    • enabled: Boolean. Enable the ssh_execute and ssh_disconnect tools.

    • connections: Object containing named connection configurations (host, port, username, password/privateKeyPath).

  • Configuration Merging: When config.json is loaded, if it contains a security or shells section, that entire section replaces the default configuration for that section. It does not merge individual fields within security or shells. The ssh section is merged more granularly. Ensure your config.json includes all necessary fields for these sections if you customize them.

Service Management (NSSM)

Once installed via install-service.ps1, you can manage the service using standard Windows tools or NSSM commands from an administrative PowerShell/CMD in the project directory:

  • Start: Start-Service MCPServer or .\nssm.exe start MCPServer

  • Stop: Stop-Service MCPServer or .\nssm.exe stop MCPServer

  • Restart: Restart-Service MCPServer or .\nssm.exe restart MCPServer

  • Status: Get-Service MCPServer or .\nssm.exe status MCPServer

  • Edit Configuration (Advanced): .\nssm.exe edit MCPServer (Opens the NSSM GUI editor)

  • View Configuration: .\nssm.exe dump MCPServer

Uninstallation (NSSM)

  1. Open PowerShell as Administrator.

  2. Navigate to the project's root directory.

  3. Execute the uninstallation script: .\uninstall-service.ps1

  4. This uses NSSM to stop and remove the MCPServer service.

Alternative Execution (Manual/Debug)

You can run the server directly without installing it as a service for testing or debugging purposes:

  1. Ensure you have run npm install.

  2. Ensure config.json exists and is configured.

  3. Open a normal terminal (PowerShell/CMD) in the project root.

  4. Run: npm run start

  5. The server will run in the foreground. Press Ctrl + C to stop it.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Available Tools

4 tools
execute_commandB

Execute a command in the specified shell (powershell, cmd, or gitbash)

Example usage (PowerShell):

{
  "shell": "powershell",
  "command": "Get-Process | Select-Object -First 5",
  "workingDir": "C:\Users\username"
}

Example usage (CMD):

{
  "shell": "cmd",
  "command": "dir /b",
  "workingDir": "C:\Projects"
}

Example usage (Git Bash):

{
  "shell": "gitbash",
  "command": "ls -la",
  "workingDir": "/c/Users/username"
}
ParametersJSON Schema
NameRequiredDescriptionDefault
commandYesCommand to execute
shellYesShell to use for command execution
workingDirNoWorking directory for command execution (optional)

TDQS

B3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of disclosing behavior. It gives examples but does not mention return values, exit codes, error handling, side effects, environment specifics, or security implications. For a command execution tool, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening one-sentence description is concise and front-loaded. The three examples are redundant in structure but serve to illustrate cross-shell syntax. Each sentence earns its place, though the examples could be trimmed to one or two without loss.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool that executes arbitrary system commands, there is no mention of output format, timeouts, working directory defaults, or safety considerations. The presence of sibling ssh_execute suggests a need to clarify local vs remote execution, which is absent. The examples help but do not fill all gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already covers 100% of parameters, but the description adds value through concrete examples showing valid shell values, command syntax, and workingDir formatting (e.g., Windows paths vs Git Bash paths). This enhances understanding beyond the schema's terse descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool executes a command in a specified shell (powershell, cmd, or gitbash), which is a specific verb+resource. It is distinguishable from siblings like get_command_history and ssh_execute, though it does not explicitly call out these differences. The mention of the shell options adds specificity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus alternatives such as ssh_execute (remote execution) or get_command_history. The examples imply usage but do not provide context, prerequisites, or exclusions. This is a clear gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_command_historyA

Get the history of executed commands

Example usage:

{
  "limit": 5
}

Example response:

[
  {
    "command": "Get-Process",
    "output": "...",
    "timestamp": "2024-03-20T10:30:00Z",
    "exitCode": 0
  }
]
ParametersJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of history entries to return (default: 10, max: 1000)

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It adds transparency by showing a detailed example response with fields (command, output, timestamp, exitCode), which clarifies the return format. However, it does not explicitly state whether history is session-scoped, how results are ordered, or that it has no side effects. Given the absence of annotations, there are notable but not critical gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise: a single opening sentence plus two compact JSON examples. The purpose is front-loaded, and every element adds value—the example usage demonstrates the parameter, and the example response shows the expected output structure. No redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter, no-output-schema tool, the description is quite complete: it states the purpose, shows how to invoke it, and provides a representative response. Minor omissions like ordering or session scope are not critical for a list-history tool. The example response effectively substitutes for an output schema, making the tool actionable for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already fully documents the 'limit' parameter with default (10) and max (1000) values, providing 100% coverage. The description's example usage (limit: 5) reinforces the parameter but adds no new semantic meaning beyond the schema. Baseline 3 is appropriate because the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a clear verb+resource statement: 'Get the history of executed commands'. It distinguishes itself from sibling tools like execute_command (execution) and ssh_execute (remote execution) by focusing specifically on retrieval of prior commands. The example response reinforces the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear usage context: to retrieve previously executed commands, with an example showing the optional limit parameter. It does not explicitly state when not to use it, but the purpose is self-evident and no competing history tools exist among siblings. No explicit exclusions are given, but this is clearly a read-only counterpart to the execution siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

ssh_disconnectA

Disconnect from an SSH server

Example usage:

{
  "connectionId": "raspberry-pi"
}

Use this to cleanly close SSH connections when they're no longer needed.

ParametersJSON Schema
NameRequiredDescriptionDefault
connectionIdYesID of the SSH connection to disconnect

TDQS

A3.9/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the full burden. It mentions 'cleanly close' but doesn't disclose side effects like what happens to associated sessions, idempotency, or error behavior. It's minimally adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and includes a practical JSON example, which helps the agent. It repeats the concept slightly ('Disconnect' and 'close SSH connections'), but overall it's well-structured and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter tool with no output schema, the description is adequate. It provides an example and clear use case. It doesn't cover errors or edge cases, but given the low complexity, this is not a significant gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with the parameter described as 'ID of the SSH connection to disconnect'. The example usage adds an illustrative value (raspberry-pi) but doesn't add semantic meaning beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Disconnect' and the resource 'SSH connection/server', which distinguishes it from siblings like ssh_execute and execute_command. The example usage reinforces the exact action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It says 'when they're no longer needed', providing clear context for when to use this tool. It doesn't explicitly mention alternatives or when not to use, but the sibling tool names imply the distinction, so a slight deduction is warranted.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

ssh_executeA

Execute a command on a remote host via SSH

Example usage:

{
  "connectionId": "raspberry-pi",
  "command": "uname -a"
}

Configuration required in config.json:

{
  "ssh": {
    "enabled": true,
    "connections": {
      "raspberry-pi": {
        "host": "raspberrypi.local",
        "port": 22,
        "username": "pi",
        "password": "raspberry"
      }
    }
  }
}
ParametersJSON Schema
NameRequiredDescriptionDefault
commandYesCommand to execute
connectionIdYesID of the SSH connection to use

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It mentions that SSH must be enabled in config.json and gives an example connection, which is useful. However, it does not disclose the command execution behavior (e.g., output format, error handling, potential destructive side-effects) or that it uses the specified password for authentication.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is structured and efficient, with a one-sentence purpose followed by illustrative JSON examples. The config block is large but necessary to show the setup requirements. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description should explain what the tool returns or what 'execute' entails. It does neither, though it does provide configuration context. For a command execution tool, the lack of mention of output or error behavior leaves a moderate gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema descriptions are minimal ('Command to execute', 'ID of the SSH connection to use'). The description adds meaningful value by showing an example usage and the config structure, clarifying that connectionId refers to a key in the 'connections' object and command is a shell string.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Execute a command on a remote host via SSH', using a specific verb and resource. It distinguishes itself from sibling tools like ssh_disconnect (manage connection) and get_command_history (retrieve history).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a concrete example and configuration requirement, implying when to use the tool (when you have a configured SSH connection and need to run a command). However, it does not explicitly state when to use it over alternatives like execute_command, nor does it provide exclusion criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 4 tool updatesv1.0.0
    • First observedexecute_command
    • First observedget_command_history
    • First observedssh_disconnect
    • First observedssh_execute
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.1/5.0

Scored across 4 tools

Disambiguation3/5

The tools have some overlap in purpose that could cause confusion. Both execute_command and ssh_execute run commands, differing only in local vs. remote execution, which might lead to misselection if the agent doesn't carefully note the distinction. However, get_command_history and ssh_disconnect are clearly distinct, and the descriptions help clarify the differences.

Naming Consistency4/5

The naming follows a consistent verb_noun pattern throughout (e.g., execute_command, get_command_history, ssh_disconnect, ssh_execute), which is predictable and readable. There are minor deviations, such as the use of 'disconnect' versus 'execute' in the SSH tools, but overall, the pattern is maintained.

Tool Count3/5

With 4 tools, the count is borderline for the server's purpose as a 'Super Windows CLI MCP Server'. It feels thin, lacking coverage for common CLI operations like file management, process control, or network utilities, which might be expected in such a domain. However, it's not severely under-scoped.

Completeness2/5

There are significant gaps in the tool surface for a Windows CLI server. It lacks basic operations like listing files, managing processes, or handling network configurations, and the SSH tools seem like an add-on rather than core functionality. This incompleteness will likely cause agent failures when trying to perform common CLI tasks.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Windows CLI MCP Server

    simon-ami
    A
    license
    B
    quality
    F
    maintenance
    A Model Context Protocol server that provides secure command-line access to Windows systems, allowing MCP clients like Claude Desktop to safely execute commands in PowerShell, CMD, and Git Bash shells with configurable security controls.
    9
    809 npm
    269
    MIT

  • Windows CLI MCP Server

    s2005
    A
    license
    A
    quality
    B
    maintenance
    Enables secure command-line interactions on Windows systems with support for PowerShell, CMD, Git Bash, and WSL shells, providing controlled file access, command execution, and configurable security restrictions.
    6
    45 npm
    4
    MIT

  • Windows CLI MCP Server

    quanticsoul4772
    A
    license
    B
    quality
    D
    maintenance
    Enables secure command-line interactions on Windows systems through PowerShell, CMD, and Git Bash, with support for SSH remote connections, SFTP file transfers, system monitoring, and configurable security controls including command blocking and path restrictions.
    34
    2
    MIT

Appeared in Searches