Skip to main content
Glama
danielklecha

mcp-server-for-powershell

by danielklecha
OverviewSchemaRelated ServersScoreDiscussions
Python

MCP server for PowerShell

PyPI PyPI Downloads License

Disclaimer

Unofficial Implementation: This project is an independent open-source software project. It is not affiliated with, endorsed by, sponsored by, or associated with Microsoft Corporation or the PowerShell team.

Trademarks: "PowerShell" and the PowerShell logo are trademarks or registered trademarks of Microsoft Corporation in the United States and/or other countries. All other trademarks cited herein are the property of their respective owners. Use of these names is for descriptive purposes only (nominative fair use) to indicate compatibility.

Related MCP server: sliverc2-mcp

Installation

  • Run directly with uv (recommended): uvx mcp-server-for-powershell

  • pip: pip install mcp-server-for-powershell

  • uv: uv pip install mcp-server-for-powershell

Configuration

The server can be configured using the following command-line arguments:

Argument

Description

Default

--allowed-commands

List of allowed PowerShell commands. If empty, all are allowed (subject to restrictions).

[]

--restricted-commands

List of restricted PowerShell commands.

Safe defaults

--restricted-directories

List of restricted directories.

System directories

--language-mode

PowerShell Language Mode: 0 (NoLanguage), 1 (ConstrainedLanguage), 2 (RestrictedLanguage), 3 (FullLanguage).

1

--cwd

Initial working directory.

Current Directory

Language Modes

  • 0 (NoLanguage): No script execution allowed.

  • 1 (ConstrainedLanguage): Restricts access to sensitive language elements (default).

  • 2 (RestrictedLanguage): Only allows basic commands.

  • 3 (FullLanguage): Unrestricted access.

Security Profiles

We recommend different configurations based on your security needs:

Default (Balanced)

By default, the server runs in ConstrainedLanguage mode with a curated blocklist of dangerous commands and restricted system directories. This provides "good enough" defaults for general use, preventing common dangerous operations while allowing most read-only and safe actions.

uvx mcp-server-for-powershell

Safe Mode (Strict)

For environments requiring stricter controls, use NoLanguage mode (--language-mode 0). Only built-in commands and cmdlets can be executed.

uvx mcp-server-for-powershell --language-mode 0

Nuclear Mode (Allow-List Only)

For the highest security "nuclear" option, explicitly whitelist ONLY the commands you need (e.g., allow get-items only). This blocks everything else by default.

uvx mcp-server-for-powershell --allowed-commands Get-Item Get-ChildItem Get-Content

License

mcp-server-for-powershell is provided as-is under the MIT license.

Available Tools

1 tool
run_powershellA
Executes PowerShell commands based on a structured JSON definition.

This tool allows you to run PowerShell commands safely strings.
It expects a JSON string that defines the command(s), parameters, pipelines, and sequences.

Args:
    json: A JSON string defining the command structure.
          Structure examples:
          1. Single Command:
             [{"command": "Get-Item", "parameters": ["."]}]

          2. .NET Static Method:
             [{"command": "[System.Math]::Sqrt", "parameters": [16]}]
             # Generates: [System.Math]::Sqrt(16)

          3. Command with Named Parameters:
             [{"command": "Get-Item", "parameters": {"-Path": "."}}]

          4. Pipeline:
             [{"command": "Get-Process", "then": {"command": "Select-Object", "parameters": ["Name"]}}]

          5. Sequence (Multiple commands):
             [{"command": "mkdir", "parameters": ["test"]}, {"command": "cd", "parameters": ["test"]}]

Returns:
    The standard output of the executed PowerShell command(s), or an error message if execution fails.
ParametersJSON Schema
NameRequiredDescriptionDefault
jsonYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.9/5.0
Behavior2/5

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

No annotations are provided, so the description must disclose behavioral traits alone. It only mentions 'Executes PowerShell commands... safely strings' (vague) and returns standard output or error. It does not disclose security implications, required permissions, sandboxing, or limitations on commands. This is insufficient for a command execution tool that could be destructive.

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 relatively long due to detailed examples, which are justified given the complexity of the input format. It is well-structured with bullet points and clear sections (Args, Returns). The main purpose is front-loaded. Could be slightly trimmed, but overall efficient for the required detail.

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?

Given the tool's potential to execute arbitrary code and the presence of an output schema (not shown), the description is moderately complete. It covers input format well but lacks details on execution environment, error handling, performance considerations, or return value structure beyond 'standard output'. This leaves gaps for an agent deciding to use the tool.

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

Parameters5/5

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

The schema has 0% description coverage for the single parameter 'json', but the description compensates richly with seven examples of valid JSON structures, covering single commands, pipelines, and sequences. This adds significant meaning beyond the schema's raw 'string' type, making it very helpful for the agent.

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 tool's purpose: 'Executes PowerShell commands based on a structured JSON definition.' The verb 'executes' and the resource 'PowerShell commands' are specific, and the JSON-based input distinguishes it from general command execution. Despite an awkward phrase ('safely strings'), the purpose is unambiguous.

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?

While there are no sibling tools, the description provides extensive guidance on how to format the input, including multiple examples of single commands, .NET methods, named parameters, pipelines, and sequences. However, it does not explicitly state when to use this tool or mention any prerequisites (e.g., PowerShell availability). The implied context is sufficient for an AI agent to understand usage.

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. Dates show when Glama detected each change.

  1. 1 tool updatev1.0.0
    • First observedrun_powershell
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap. The agent can uniquely identify the tool's purpose without ambiguity.

Naming Consistency5/5

The single tool name follows a clear verb_noun pattern (run_powershell), which is consistent and readable. Since there's only one tool, no convention conflicts exist.

Tool Count3/5

The server has only one tool for the broad domain of PowerShell execution. While the tool is versatile, it forces the agent to encode all operations as complex JSON, which is less ergonomic than dedicated tools for common tasks. The count is borderline.

Completeness4/5

The single tool can theoretically execute any PowerShell command, covering the domain of command execution comprehensively. However, it lacks specialized tools for session management, script handling, or error recovery, which may be needed for complex workflows.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/danielklecha/mcp-server-for-powershell'

If you have feedback or need assistance with the MCP directory API, please join our Discord server