Skip to main content
Glama
gunjanjp

PowerShell MCP Server

by gunjanjp
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Local

PowerShell MCP Server

A comprehensive Model Context Protocol (MCP) server that enables Claude and other LLM applications to execute PowerShell commands, scripts, and perform system operations on Windows systems.

🌟 Key Features

  • 🔧 PowerShell Execution: Execute commands, run scripts, and create new PowerShell files

  • 🖥️ System Monitoring: Get system info, monitor processes, check services and disk space

  • 📁 File Operations: List directories, get file info, and search files with pattern matching

  • ⚙️ Simple Setup: One-command installation with automatic Claude Desktop configuration

  • 🛡️ Secure: Safe execution with proper error handling and session management

Related MCP server: Claude MCP Command Server

🛠️ Available Tools

PowerShell Tools

  • execute-powershell - Execute PowerShell commands with optional working directory

  • execute-powershell-script - Run PowerShell script files with parameters

  • create-powershell-script - Create new PowerShell scripts

System Tools

  • get-system-info - Comprehensive Windows system information

  • get-process-list - Running processes with CPU/memory usage (sortable/filterable)

  • get-service-status - Windows services status with filtering

  • check-disk-space - Disk space usage for all or specific drives

File Tools

  • list-directory - Enhanced directory listing with filtering

  • get-file-info - Detailed file and directory metadata

  • search-files - Recursive file search with pattern matching

📋 Prerequisites

  • Windows 10/11 or Windows Server 2016+

  • Node.js 18.0.0 or higher

  • PowerShell 5.1+ or PowerShell Core 7+

  • Claude Desktop application

🚀 Quick Setup

Option 1: Safe Automated Setup (Recommended)

# Clone and setup with configuration management
git clone https://github.com/gunjanjp/powershell-mcp.git
cd powershell-mcp
complete-setup.bat

Option 2: Configuration Recovery (If you had existing settings)

# If previous setup overwrote your existing configuration
node recovery.js status      # Check current state
node recovery.js scan        # Find backup configurations
node recovery.js restore 1   # Restore from backup
# OR
node recovery.js merge 1     # Merge backup with current config

Option 3: Manual Setup

# Clone the repository
git clone https://github.com/gunjanjp/powershell-mcp.git
cd powershell-mcp

# Install dependencies
npm install

# Safely add to existing configuration
node recovery.js add-powershell

# Restart Claude Desktop

📖 Usage Examples

Ask Claude:

  • "Execute PowerShell: Get-Date"

  • "Check my system information"

  • "Show me the top 10 processes by CPU usage"

  • "What's my disk space usage?"

  • "List files in my Downloads folder"

  • "Search for all .txt files in C:\Users"

  • "Create a PowerShell script to backup my Documents folder"

🔧 Commands

Server Commands

# Start the server
npm start

# Test components
npm test

# Run diagnostics
node diagnose.bat

# Start server directly  
node src/server.js

Configuration Management

# Check configuration status
node recovery.js status

# Find backup configurations
node recovery.js scan

# Safely add PowerShell server
node recovery.js add-powershell

# Restore from backup
node recovery.js restore <number>

# Merge configurations
node recovery.js merge <number>

# Show backup contents
node recovery.js show <number>

Quick Setup Commands

# Complete setup with safety checks
complete-setup.bat

# Test server only
run-test.bat

📁 Project Structure

powershell-mcp/
├── src/
│   ├── server.js           # Main MCP server (with stderr logging fix)
│   ├── tools/              # Tool implementations
│   │   ├── powershell-tools.js
│   │   ├── system-tools.js
│   │   └── file-tools.js
│   └── utils/              # Utility modules
│       └── system-utils.js
├── examples/               # Example PowerShell scripts
├── scripts/               # Setup utilities
├── test/                  # Test files
├── claude_desktop_config.json  # Claude Desktop configuration
├── setup.bat             # Automated setup script
├── diagnose.bat          # Diagnostic tool
├── test-server.js        # Component testing
└── README.md

⚙️ Claude Desktop Configuration

The server uses this configuration (automatically applied by setup):

{
  "mcpServers": {
    "powershell": {
      "command": "node",
      "args": ["D:/claude/claude-powershell-mcp/src/server.js"],
      "env": {}
    }
  }
}

Config location: %APPDATA%\Claude\claude_desktop_config.json

🛡️ Security Features

  • Safe Execution: Uses -ExecutionPolicy Bypass and -NoProfile for security

  • Input Validation: All inputs validated with Zod schemas

  • Session Management: PowerShell sessions properly disposed after use

  • Error Handling: Comprehensive error handling prevents system issues

  • Logging: All operations logged to stderr (not interfering with JSON-RPC)

🐛 Troubleshooting

Server won't start

# Check Node.js version (need 18+)
node --version

# Check dependencies
npm install

# Test components
node test-server.js

Claude Desktop integration issues

# Run setup again
setup.bat

# Check configuration
type "%APPDATA%\Claude\claude_desktop_config.json"

# Restart Claude Desktop completely

PowerShell execution issues

# Test PowerShell
powershell -Command "Get-Date"

# Check execution policy
Get-ExecutionPolicy

# Run diagnostics
node diagnose.bat

🔄 Recent Updates (v1.1.2)

Configuration Management Improvements

  • ✅ Safe Configuration Management - No more overwriting existing configs

  • ✅ Automatic Backups - Creates backups before any configuration changes

  • ✅ Configuration Recovery - Tools to find and restore previous configurations

  • ✅ Merge Capability - Intelligent merging of multiple MCP server configs

  • ✅ Interactive Recovery - Step-by-step configuration recovery process

Previous Fixes (v1.1.1)

  • ✅ Fixed Claude Desktop JSON parsing error - Changed console.log to console.error (stderr)

  • ✅ Cleaned up project structure - Removed redundant server files

  • ✅ Simplified setup - One script setup process

  • ✅ Proper error handling - Enhanced logging and error management

🤝 Contributing

  1. Fork the repository

  2. Create feature branch: git checkout -b feature-name

  3. Make changes and test: npm test

  4. Commit: git commit -am 'Add feature'

  5. Push: git push origin feature-name

  6. Submit pull request

📄 License

MIT License - see LICENSE file for details.

🔗 Links

Made with ❤️ for the Claude and PowerShell communities

⚠️ Important: This tool provides direct access to PowerShell commands. Use responsibly and be aware of security implications.

Available Tools

10 tools
check-disk-spaceA

Check disk space usage for all drives or a specific drive

ParametersJSON Schema
NameRequiredDescriptionDefault
driveNoOptional drive letter (e.g., "C:", "D:") to check specific drive

TDQS

A3.9/5.0
Behavior2/5

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

No annotations provided; the description does not disclose behavioral traits such as read-only nature, performance impact, or permission requirements. For a tool that is likely safe and read-only, this lack of transparency is a gap.

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 a single sentence that is direct and front-loaded with the key action, containing no unnecessary words.

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

Completeness5/5

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

Given the simple nature of the tool (one optional parameter, no output schema), the description sufficiently conveys its purpose and scope for an agent to invoke it correctly.

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%, so the description adds minimal value beyond the schema. It mentions 'all drives or a specific drive', but does not elaborate on format or behavior.

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 uses a clear verb 'Check' and resource 'disk space usage', and distinguishes from sibling tools like get-system-info by focusing specifically on disk space.

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 states when to use the tool (checking all drives or a specific drive), but does not provide guidance on when not to use it or mention alternatives among siblings.

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

create-powershell-scriptB

Create a new PowerShell script file with specified content

ParametersJSON Schema
NameRequiredDescriptionDefault
scriptPathYesPath where to create the PowerShell script (.ps1)
contentYesPowerShell script content
executableNoMake the script executable (default: true)

TDQS

B3.1/5.0
Behavior2/5

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

Description lacks behavioral details beyond the basic action. No annotations provided, so description carries full burden. It does not disclose file overwrite behavior, permissions needed, or any side effects.

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?

Single sentence is concise and to the point, but could include more useful information without becoming verbose.

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?

No output schema exists, yet description does not explain return values or behavior upon completion. Lacks completeness for a create operation.

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?

Input schema covers 100% of parameters with descriptions. The description adds no additional meaning beyond the schema, so baseline 3 is appropriate.

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 'Create', the resource 'PowerShell script file', and the action 'with specified content'. It distinguishes from sibling tools like 'execute-powershell-script' which are about execution, not creation.

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 on when to use this tool versus alternatives like 'execute-powershell-script'. No mention of prerequisites or scenarios where creation is appropriate.

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

execute-powershellC

Execute a PowerShell command with optional working directory

ParametersJSON Schema
NameRequiredDescriptionDefault
commandYesThe PowerShell command to execute
workingDirectoryNoOptional working directory for command execution

TDQS

C2.9/5.0
Behavior2/5

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

The description lacks behavioral details beyond the basic action. It does not disclose what happens on error, whether output is returned, security implications, side effects, or any constraints. With no annotations, this is a significant gap.

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 a single sentence with no extraneous words. It is efficiently front-loaded, though it sacrifices detail for brevity.

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?

Given the absence of an output schema, the description should explain return values or output format. It also lacks error handling details. For a tool that executes commands, this is insufficiently complete.

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 schema already provides descriptions for both parameters (100% coverage). The description adds no extra meaning beyond what the schema states, so the baseline score of 3 is appropriate.

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 verb 'execute' and resource 'PowerShell command', along with the optional working directory. However, it does not differentiate from the sibling tool 'execute-powershell-script', which likely executes a PowerShell script file rather than a direct command.

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 provided about when to use this tool versus alternatives. There is no mention of prerequisites, when not to use it, or context about the sibling tools that might be more appropriate for script execution.

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

execute-powershell-scriptB

Execute a PowerShell script file with optional parameters

ParametersJSON Schema
NameRequiredDescriptionDefault
scriptPathYesPath to the PowerShell script file (.ps1)
parametersNoOptional parameters to pass to the script
workingDirectoryNoOptional working directory for script execution

TDQS

B3.1/5.0
Behavior2/5

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

With no annotations, the description must disclose behavioral traits. It fails to mention security implications, execution context, side effects, or error behavior, which are critical for a script execution tool.

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 a single, efficient sentence with no redundancy. It could include more context, but it is appropriately concise.

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?

Given no output schema and no annotations, the description lacks details on return values, success/failure conditions, and error handling, leaving the agent underinformed.

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%, and the description adds no extra meaning beyond 'with optional parameters', which is already evident from the schema. 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 'Execute' and the resource 'PowerShell script file', specifying it includes optional parameters. It distinguishes from siblings like 'execute-powershell' (likely inline execution) and 'create-powershell-script' (creation).

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?

The description provides no guidance on when to use this tool versus alternatives (e.g., 'execute-powershell' for inline commands) or any prerequisites/restrictions.

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

get-file-infoC

Get detailed information about a file or directory

ParametersJSON Schema
NameRequiredDescriptionDefault
pathYesPath to the file or directory

TDQS

C2.9/5.0
Behavior2/5

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

The description uses 'detailed information' but does not specify what fields or properties are returned (e.g., size, type, permissions). No annotations are provided, so the description carries the full burden. It omits important behavioral traits like whether it is read-only or requires permissions.

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 a single, concise sentence. It is appropriately sized for a simple tool but lacks structure like bullet points or explicit formatting. It is front-loaded with the core action.

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?

Given the absence of an output schema, the description should explain what 'detailed information' includes. It does not, leaving uncertainty about return values. This is a notable gap for a tool with one parameter and no output schema.

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 one parameter ('path') described as 'Path to the file or directory'. The description adds no extra meaning beyond the schema. Baseline 3 is appropriate as the schema does the work, but the description adds no additional value.

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 'Get detailed information about a file or directory', which is a specific verb and resource. It distinguishes from sibling tools like list-directory (which lists contents) and search-files (which finds files) by focusing on detailed info of a single item, though it does not explicitly differentiate.

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 on when to use this tool versus alternatives. It does not mention exclusions, prerequisites, or context that would help an agent decide between this and similar tools like get-system-info or check-disk-space.

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

get-process-listA

Get list of running processes with CPU and memory usage, optionally filtered by name

ParametersJSON Schema
NameRequiredDescriptionDefault
processNameNoOptional process name filter
sortByNoSort processes by CPU, Memory, or NameCPU
limitNoMaximum number of processes to return (default: 10)

TDQS

A3.5/5.0
Behavior3/5

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

No annotations are provided, so the description carries full burden. It indicates a read-only operation returning process details, but does not mention potential side effects, permissions, or real-time nature. Adequate but not explicit.

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?

Single sentence with no wasted words. Front-loaded with verb and resource.

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, the description should hint at return structure (e.g., array of objects). It does not. Adequate for a simple list but lacks error handling or empty results behavior.

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%, so the schema fully describes parameters. The description only reinforces the optional filter, adding no new meaning beyond schema.

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 retrieves a list of running processes with CPU and memory usage, with optional name filtering. It distinguishes from sibling tools like get-system-info or get-service-status.

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 on when to use this tool vs alternatives like get-system-info. The description does not specify when filtering by name is beneficial or any prerequisites.

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

get-service-statusB

Get Windows service status, optionally filtered by service name or status

ParametersJSON Schema
NameRequiredDescriptionDefault
serviceNameNoOptional service name filter
statusNoFilter by service statusAll

TDQS

B3.3/5.0
Behavior3/5

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

No annotations are provided, so the description must carry behavioral disclosure. It indicates a read operation, but does not mention permissions, error handling, or output format. Adequate for a simple tool but lacks depth.

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 a single clear sentence with no wasted words. It is front-loaded with the verb. Slight deduction for missing usage details that could be added without length.

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?

No output schema exists, and the description does not specify what the returned data looks like (e.g., list of services, status objects). Lacks prerequisites or use-case context, leaving an agent to infer functionality.

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 covers both parameters with descriptions. The description adds minimal value beyond the schema, restating the optional filters. Baseline 3 as 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 clearly states the action (Get), the resource (Windows service status), and indicates optional filtering by service name or status. It is specific and distinguishes from sibling tools like get-system-info or get-process-list.

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 provided on when to use this tool versus alternatives. The description only states what it does, without specifying context or exclusions.

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

get-system-infoB

Get comprehensive Windows system information including hardware, OS, and performance metrics

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations, the description carries full burden but only states it 'gets' info. It doesn't disclose whether the operation is safe/read-only, if authentication is required, or any rate limits or side effects.

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?

A single sentence that is front-loaded with the verb 'Get' and specific resource. 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?

Given no output schema and a broad scope, the description is minimal. It lists categories (hardware, OS, performance) but does not detail specific metrics, which would aid agent understanding of what to expect.

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?

There are no parameters, so the definition naturally has 100% schema coverage. The description need not add parameter info; a baseline of 4 is appropriate.

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 it retrieves comprehensive Windows system info including hardware, OS, and performance, distinguishing it from sibling tools that target specific areas (e.g., check-disk-space, get-process-list).

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 on when to use this tool versus alternatives. It does not mention scenarios where a more specific tool (e.g., get-process-list) would be preferable or that this is a catch-all for a broad overview.

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

list-directoryC

List contents of a directory with detailed information

ParametersJSON Schema
NameRequiredDescriptionDefault
pathYesDirectory path to list
detailedNoShow detailed information (like ls -la)
filterNoOptional file filter pattern (e.g., "*.txt", "*.ps1")

TDQS

C2.9/5.0
Behavior2/5

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

No annotations; description only mentions 'detailed information' which mirrors the parameter. No disclosure of performance, access rights, or output structure.

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?

One clear sentence; appropriately short for a simple tool. Could be expanded with usage hints but not overly verbose.

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?

No output schema; description fails to explain what the output contains (e.g., file names, sizes). Incomplete for agent decision-making.

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 basic descriptions. The tool description adds no extra meaning beyond what the schema provides, so baseline 3 applies.

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 lists directory contents with detailed information. It distinguishes from sibling tools like search-files and get-file-info, but doesn't explicitly differentiate.

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 on when to use this tool versus alternatives (e.g., search-files). No exclusions or context provided.

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

search-filesB

Search for files and directories matching a pattern

ParametersJSON Schema
NameRequiredDescriptionDefault
searchPathYesDirectory path to search in
patternYesSearch pattern (supports wildcards like *.txt, *config*)
recursiveNoSearch recursively in subdirectories
limitNoMaximum number of results to return

TDQS

B3.1/5.0
Behavior2/5

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

No annotations provided, so description must convey behavioral traits. It only says 'search', which implies read-only, but does not explicitly confirm or disclose any other traits like performance or side effects.

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?

Single sentence, no wasted words. Front-loaded with purpose. Could be slightly more informative without becoming verbose.

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?

No output schema; description does not describe return format, behavior on no matches, or error conditions. For a tool with 4 parameters, more context is needed.

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 description coverage is 100%, so the schema already documents parameters. The tool description does not add extra meaning beyond that.

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?

Description clearly states 'Search for files and directories matching a pattern', using a specific verb and resource. It distinguishes from sibling tools like 'list-directory' and 'get-file-info'.

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 explicit when-to-use or when-not-to-use guidance. The description implies pattern-based searching but does not mention alternatives or context for use.

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. 10 tool updatesv1.1.1
    • First observedcheck-disk-space
    • First observedcreate-powershell-script
    • First observedexecute-powershell
    • First observedexecute-powershell-script
    • First observedget-file-info
    • First observedget-process-list
    • First observedget-service-status
    • First observedget-system-info
    • First observedlist-directory
    • First observedsearch-files
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0
Disambiguation4/5

Tools are mostly distinct with clear purposes. Slight overlap between list-directory and search-files, but descriptions differentiate them. Other tools like check-disk-space and get-system-info are unique.

Naming Consistency5/5

All tool names follow a consistent verb-noun pattern with hyphens (e.g., check-disk-space, get-process-list). No mixing of styles or vague verbs.

Tool Count5/5

With 10 tools, the server is well-scoped. It covers core PowerShell administration tasks without being overcrowded or too sparse.

Completeness3/5

The surface covers basic system info and file operations but lacks update/delete for files, process management (start/stop), and service management (start/stop). These are notable gaps given the 'PowerShell' domain.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

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

  • Claude MCP Command Server

    kimjungyeol
    F
    license
    Not graded
    quality
    D
    maintenance
    A server implementation for the Model Context Protocol (MCP) that allows Claude AI to execute commands through a command-line interface, enabling direct system interactions from within Claude.
    -

  • Windows System MCP

    guangxiangdebizi
    A
    license
    A
    quality
    D
    maintenance
    A comprehensive Model Context Protocol server that enables AI assistants to interact with and manage Windows systems, providing capabilities for file system operations, process management, system information retrieval, registry operations, service management, network diagnostics, and performance monitoring.
    7
    19
    5
    Apache 2.0

  • MCP Complete Implementation

    saksham0712
    F
    license
    B
    quality
    D
    maintenance
    Provides a complete end-to-end MCP server implementation with file system tools, web scraping capabilities, and system information access. Includes ready-to-use configuration files and integration examples for Claude Desktop, ChatGPT, and other AI models.
    6
    -

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/gunjanjp/powershell-mcp'

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