The Super Shell MCP Server enables secure, cross-platform execution of shell commands with comprehensive whitelisting and approval workflows across Windows, macOS, and Linux.
• Execute shell commands on any platform with automatic detection of shells (cmd.exe, PowerShell, zsh, bash, sh) and prevention of shell injection using Node.js's execFile
• Manage command whitelists with three security levels: safe (no approval needed), requires_approval (needs explicit approval), and forbidden (blocked)
• Handle approval workflows through non-blocking processes to approve/deny pending commands by ID with optional reasons
• Retrieve platform information for diagnostic purposes about the current operating system and shell configuration
• Customize security settings by adding, updating, or removing commands from whitelists with custom security levels and descriptions
• Monitor operations through comprehensive logging of server operations, command execution, and approval workflows
• View system status including current whitelist and pending command queue
Provides Linux-specific shell integration with support for bash, sh, and zsh shells, along with platform-appropriate command whitelists.
Supports macOS-specific shell environments (zsh, bash, sh) with tailored command whitelists and security considerations for the platform.
Enables execution of shell commands across multiple platforms (Windows, macOS, Linux) with platform-specific command whitelists and security levels.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Super Shell MCP Server list all files in the current directory"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server for executing shell commands across multiple platforms (Windows, macOS, Linux). This server provides a secure way to execute shell commands with built-in whitelisting and approval mechanisms.
🎉 Now available as a Claude Desktop Extension! Install with one click using the
.dxtpackage - no developer tools or configuration required.
Execute shell commands through MCP on Windows, macOS, and Linux
Automatic platform detection and shell selection
Support for multiple shells:
Windows: cmd.exe, PowerShell
macOS: zsh, bash, sh
Linux: bash, sh, zsh
Shell parsing disabled by default to eliminate command-injection risk, with an explicit opt-in mode for trusted workflows
Command whitelisting with security levels:
Safe: Commands that can be executed without approval
Requires Approval: Commands that need explicit approval before execution
Forbidden: Commands that are explicitly blocked
Platform-specific command whitelists
Non-blocking approval workflow for potentially dangerous commands
Comprehensive logging system with file-based logs
Comprehensive command management tools
Platform information tool for diagnostics
Related MCP server: Mac Shell MCP Server
One-Click Installation for Claude Desktop:
Download the super-shell-mcp.dxt file from the latest release
Quick Install: Double-click the .dxt file while Claude Desktop is open
OR
Manual Install:
Open Claude Desktop
Go to Settings > Extensions
Click "Add Extension"
Select the downloaded super-shell-mcp.dxt file
Configure (optional): Set custom shell path if needed
Start using - The extension is ready to use immediately!
✅ Benefits of DXT Installation:
No developer tools required (Node.js, Python, etc.)
No manual configuration files
Automatic dependency management
One-click installation and updates
Secure credential storage in OS keychain
To install Super Shell MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @cfdude/super-shell-mcp --client claude# Clone the repository
git clone https://github.com/cfdude/super-shell-mcp.git
cd super-shell-mcp
# Install dependencies
npm install
# Build the project
npm run buildIf you installed using the .dxt extension (Option 1), you're ready to go! No additional configuration needed. The extension handles everything automatically:
✅ Automatic startup when Claude Desktop launches
✅ Platform detection and appropriate shell selection
✅ Built-in security with command whitelisting and approval workflows
✅ Optional configuration via Claude Desktop's extension settings
If you installed manually (Option 2 or 3), you'll need to configure Claude Desktop or your MCP client:
npm startOr directly:
node build/index.jsFor manual installations, both Roo Code and Claude Desktop use a similar configuration format for MCP servers:
The easiest way to use Super Shell MCP is with NPX, which automatically installs and runs the package from npm without requiring manual setup. The package is available on NPM at https://www.npmjs.com/package/super-shell-mcp.
"super-shell": {
"command": "npx",
"args": [
"-y",
"super-shell-mcp"
],
"alwaysAllow": [],
"disabled": false
}"super-shell": {
"command": "npx",
"args": [
"-y",
"super-shell-mcp"
],
"alwaysAllow": false,
"disabled": false
}If you prefer to use a local installation, add the following to your Roo Code MCP settings configuration file (located at ~/Library/Application Support/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json):
"super-shell": {
"command": "node",
"args": [
"/path/to/super-shell-mcp/build/index.js"
],
"alwaysAllow": [],
"disabled": false
}You can optionally provide a trusted shell and opt into shell parsing by setting environment variables instead of command-line flags:
"super-shell": {
"command": "node",
"args": [
"/path/to/super-shell-mcp/build/index.js"
],
"env": {
"CUSTOM_SHELL": "/usr/bin/bash",
"SUPER_SHELL_USE_SHELL": "true"
},
"alwaysAllow": [],
"disabled": false
}Windows 11 example:
"super-shell": {
"command": "C:\\Program Files\\nodejs\\node.exe",
"args": [
"C:\\Program Files\\nodejs\\node_modules\\npm\\bin\\npx-cli.js",
"-y",
"super-shell-mcp",
"C:\\Users\\username"
],
"env": {
"CUSTOM_SHELL": "C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\powershell.exe",
"SUPER_SHELL_USE_SHELL": "true"
},
"alwaysAllow": [],
"disabled": false
}Add the following to your Claude Desktop configuration file (located at ~/Library/Application Support/Claude/claude_desktop_config.json):
"super-shell": {
"command": "node",
"args": [
"/path/to/super-shell-mcp/build/index.js"
],
"alwaysAllow": false,
"disabled": false
}For Windows users, the configuration file is typically located at %APPDATA%\Claude\claude_desktop_config.json.
Default shell: cmd.exe (or PowerShell if available)
Configuration paths:
Roo Code: %APPDATA%\Code\User\globalStorage\rooveterinaryinc.roo-cline\settings\cline_mcp_settings.json
Claude Desktop: %APPDATA%\Claude\claude_desktop_config.json
Shell path examples:
cmd.exe: C:\\Windows\\System32\\cmd.exe
PowerShell: C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\powershell.exe
PowerShell Core: C:\\Program Files\\PowerShell\\7\\pwsh.exe
Default shell: /bin/zsh
Configuration paths:
Roo Code: ~/Library/Application Support/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json
Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json
Shell path examples:
zsh: /bin/zsh
bash: /bin/bash
sh: /bin/sh
Default shell: /bin/bash (or $SHELL environment variable)
Configuration paths:
Roo Code: ~/.config/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json
Claude Desktop: ~/.config/Claude/claude_desktop_config.json
Shell path examples:
bash: /bin/bash
sh: /bin/sh
zsh: /usr/bin/zsh
Shell parsing is disabled by default for security. Customise behaviour with the following environment variables:
SUPER_SHELL_USE_SHELL: set to true (or 1/yes/on) to enable shell parsing for trusted workflows. Omit or set to false to keep the safer default.
CUSTOM_SHELL: optional path to the shell executable used when shell parsing is enabled.
SUPER_SHELL_COMMAND_TIMEOUT: optional override (milliseconds) for the default 30s command timeout.
⚠️ Enabling shell parsing reintroduces the risk of command injection. Only enable it when you fully trust the command source and payload.
Replace /path/to/super-shell-mcp with the actual path where you cloned the repository.
Note:
For Roo Code: Setting
alwaysAllowto an empty array[]is recommended for security reasons, as it will prompt for approval before executing any commands. If you want to allow specific commands without prompting, you can add their names to the array, for example:"alwaysAllow": ["execute_command", "get_whitelist"].For Claude Desktop: Setting
alwaysAllowtofalseis recommended for security reasons. Claude Desktop uses a boolean value instead of an array, wherefalsemeans all commands require approval andtruemeans all commands are allowed without prompting.Important: The
alwaysAllowparameter is processed by the MCP client (Roo Code or Claude Desktop), not by the Super Shell MCP server itself. The server will work correctly with either format, as the client handles the approval process before sending requests to the server.
The server exposes the following MCP tools:
get_platform_infoGet information about the current platform and shell.
{}execute_commandExecute a shell command on the current platform.
{
"command": "ls",
"args": ["-la"]
}get_whitelistGet the list of whitelisted commands.
{}add_to_whitelistAdd a command to the whitelist.
{
"command": "python3",
"securityLevel": "safe",
"description": "Run Python 3 scripts"
}update_security_levelUpdate the security level of a whitelisted command.
{
"command": "python3",
"securityLevel": "requires_approval"
}remove_from_whitelistRemove a command from the whitelist.
{
"command": "python3"
}get_pending_commandsGet the list of commands pending approval.
{}approve_commandApprove a pending command.
{
"commandId": "command-uuid-here"
}deny_commandDeny a pending command.
{
"commandId": "command-uuid-here",
"reason": "This command is potentially dangerous"
}The server includes platform-specific command whitelists that are automatically selected based on the detected platform.
echo - Print text to standard output
ls - List directory contents
pwd - Print working directory
echo - Print text to standard output
cat - Concatenate and print files
grep - Search for patterns in files
find - Find files in a directory hierarchy
cd - Change directory
head - Output the first part of files
tail - Output the last part of files
wc - Print newline, word, and byte counts
dir - List directory contents
type - Display the contents of a text file
findstr - Search for strings in files
where - Locate programs
whoami - Display current user
hostname - Display computer name
ver - Display operating system version
copy - Copy files
move - Move files
mkdir - Create directories
rmdir - Remove directories
rename - Rename files
attrib - Change file attributes
mv - Move (rename) files
cp - Copy files and directories
mkdir - Create directories
touch - Change file timestamps or create empty files
chmod - Change file mode bits
chown - Change file owner and group
del - Delete files
erase - Delete files
format - Format a disk
runas - Execute a program as another user
rm - Remove files or directories
sudo - Execute a command as another user
All commands are executed with the permissions of the user running the MCP server
Commands requiring approval are held in a queue until explicitly approved
Forbidden commands are never executed
The server uses Node.js's execFile instead of exec to prevent shell injection
Arguments are validated against allowed patterns when specified
You can extend the whitelist by using the add_to_whitelist tool. For example:
{
"command": "npm",
"securityLevel": "requires_approval",
"description": "Node.js package manager"
}Super Shell MCP is available as an npm package at https://www.npmjs.com/package/super-shell-mcp.
Using the NPX method (as shown in Option 1 of the Configuration section) offers several advantages:
No Manual Setup: No need to clone the repository, install dependencies, or build the project
Automatic Updates: Always uses the latest published version
Cross-Platform Compatibility: Works the same way on Windows, macOS, and Linux
Simplified Configuration: Shorter configuration with no absolute paths
Reduced Maintenance: No local files to manage or update
If you prefer to use the latest development version directly from GitHub:
"super-shell": {
"command": "npx",
"args": [
"-y",
"github:cfdude/super-shell-mcp"
],
"alwaysAllow": [], // For Roo Code
"disabled": false
}If you want to publish your own modified version to npm:
Update the package.json with your details
Ensure the "bin" field is properly configured:
"bin": {
"super-shell-mcp": "./build/index.js"
}Publish to npm:
npm publishFor optimal integration with MCP clients using NPX, this project follows these best practices:
Executable Entry Point: The main file includes a shebang line (#!/usr/bin/env node) and is made executable during build.
Package Configuration:
"type": "module" - Ensures ES Modules are used
"bin" field - Maps the command name to the entry point
"files" field - Specifies which files to include when publishing
"prepare" script - Ensures compilation happens on install
TypeScript Configuration:
"module": "NodeNext" - Proper ES Modules support
"moduleResolution": "NodeNext" - Consistent with ES Modules
Automatic Installation and Execution:
The MCP client configuration uses npx -y to automatically install and run the package
No terminal window is tied up as the process runs in the background
Publishing Process:
# Update version in package.json
npm version patch # or minor/major as appropriate
# Build and publish
npm publishThese practices ensure the MCP server can be started automatically by the MCP client without requiring a separate terminal window, improving user experience and operational efficiency.
PowerShell Script Execution Policy
Issue: PowerShell may block script execution with the error "Execution of scripts is disabled on this system"
Solution: Run PowerShell as Administrator and execute Set-ExecutionPolicy RemoteSigned or use the -ExecutionPolicy Bypass parameter when configuring the shell
Path Separators
Issue: Windows uses backslashes (\) in paths, which need to be escaped in JSON
Solution: Use double backslashes (\\) in JSON configuration files, e.g., C:\\Windows\\System32\\cmd.exe
Command Not Found
Issue: Windows doesn't have Unix commands like ls, grep, etc.
Solution: Use Windows equivalents (dir instead of ls, findstr instead of grep)
Shell Permissions
Issue: Permission denied when executing commands
Solution: Ensure the shell has appropriate permissions with chmod +x /path/to/shell
Environment Variables
Issue: Environment variables not available in MCP server
Solution: Set environment variables in the shell's profile file (.zshrc, .bashrc, etc.)
Shell Detection Issues
Issue: Server fails to detect the correct shell
Solution: Explicitly specify the shell path in the configuration
Command Execution Timeout
Issue: Commands taking too long and timing out
Solution: Increase the timeout value in the command service constructor
The server includes a comprehensive logging system that writes logs to a file for easier debugging and monitoring:
Log File Location
Default: logs/super-shell-mcp.log in the server's directory
The logs directory is created automatically and tracked by Git (with a .gitkeep file)
Log files themselves are excluded from Git via .gitignore
Contains detailed information about server operations, command execution, and approval workflow
Log Levels
INFO: General operational information
DEBUG: Detailed debugging information
ERROR: Error conditions and exceptions
Viewing Logs
Use standard file viewing commands to check logs:
# View the entire log
cat logs/super-shell-mcp.log
# Follow log updates in real-time
tail -f logs/super-shell-mcp.logLog Content
Server startup and configuration
Command execution requests and results
Approval workflow events (pending, approved, denied)
Error conditions and troubleshooting information
Whitelist Management
Issue: Need to add custom commands to whitelist
Solution: Use the add_to_whitelist tool to add commands specific to your environment
Affected Version: Android Studio Otter 2 Feature Drop | 2025.2.2 Canary 3 (Build #AI-252.25557.131.2522.14357309)
Issue: Android Studio's MCP client implementation incorrectly serializes array parameters as strings when calling the execute_command tool. This causes commands with arguments to fail with the error:
Error: Expected array, received stringExample:
// This fails in Android Studio Otter 2
execute_command(
command = "git",
args = ["add", "."] // Sent as string '["add", "."]' instead of array
)Root Cause: This is a bug in Android Studio's MCP client, not in super-shell-mcp. The server correctly defines args as type array in its schema, and the issue has been verified to work correctly with:
Claude Desktop
Official MCP SDK clients
Other MCP-compatible tools
Status: This is an Android Studio bug. The super-shell-mcp server implements the MCP specification correctly.
Workaround: None currently available. Users experiencing this issue should report it to the Android Studio/JetBrains team.
References:
Issue reported: #20
Related documentation: Android Studio Gemini MCP Integration
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Add a command to the whitelist
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | The command to whitelist | |
| securityLevel | Yes | Security level for the command | |
| description | No | Description of the command |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('Add') but doesn't explain what happens upon invocation—e.g., whether it's a mutation, requires permissions, has side effects like notifications, or returns confirmation. This leaves significant gaps for a tool that modifies a security list.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero waste—it directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of modifying a security whitelist, no annotations, and no output schema, the description is incomplete. It doesn't cover behavioral aspects like mutation effects, error conditions, or return values, which are crucial for safe tool invocation in this context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 all three parameters (command, securityLevel, description) with details like enum values for securityLevel. The description adds no additional meaning beyond the schema, resulting in the baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Add') and resource ('command to the whitelist'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'update_security_level' or 'remove_from_whitelist', which prevents a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 like 'update_security_level' or 'approve_command'. The description lacks context about prerequisites, such as whether the command must be pending or already exist, leaving usage unclear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Approve a pending command
| Name | Required | Description | Default |
|---|---|---|---|
| commandId | Yes | ID of the command to approve |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. 'Approve' implies a mutation that changes state, but the description doesn't clarify what happens after approval (e.g., does it trigger execution, log the action, or require additional steps?), potential side effects, permission requirements, or error conditions. This leaves significant gaps for a tool that likely involves security-sensitive operations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, direct sentence with no wasted words. It front-loads the core action and resource efficiently, making it easy to parse and understand at a glance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, and the tool's likely role in a security/command workflow (inferred from sibling tools), the description is insufficient. It doesn't explain the outcome of approval, how it interacts with other tools (e.g., 'execute_command'), or any system constraints, leaving the agent with incomplete context for safe and effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with the single parameter 'commandId' clearly documented in the schema. The description adds no additional parameter semantics beyond implying that 'commandId' refers to a pending command, which is already inferred from the tool's purpose. This meets the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('approve') and the target resource ('a pending command'), which is specific and unambiguous. However, it doesn't differentiate this tool from its sibling 'deny_command' beyond the opposite action, nor does it explain what 'approve' entails in this context versus simply executing or modifying the command.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 like 'deny_command' or 'execute_command'. It doesn't specify prerequisites (e.g., that the command must be in a pending state) or contextual cues for selection, leaving the agent to infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Deny a pending command
| Name | Required | Description | Default |
|---|---|---|---|
| commandId | Yes | ID of the command to deny | |
| reason | No | Reason for denial |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states the action ('deny') but doesn't explain what 'deny' entails—whether it's reversible, if it requires specific permissions, what the outcome is, or if there are side effects. For a mutation tool with zero annotation coverage, this leaves significant gaps in understanding the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero wasted words. It's front-loaded with the core action and target, making it easy to parse quickly. Every word earns its place by conveying essential information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that this is a mutation tool with no annotations and no output schema, the description is incomplete. It doesn't explain the tool's behavior, outcomes, or error conditions. The agent lacks context on what 'deny' means operationally, making it difficult to use correctly without additional information.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with clear documentation for both parameters ('commandId' and 'reason'). The description doesn't add any meaning beyond what the schema provides, such as format examples or constraints. Since schema coverage is high, the baseline score of 3 is appropriate, as the schema handles parameter semantics adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('deny') and the target ('a pending command'), providing a specific verb+resource combination. However, it doesn't differentiate from sibling tools like 'approve_command' or explain what 'deny' means in this context beyond the basic action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 like 'approve_command' or 'execute_command'. It doesn't mention prerequisites (e.g., needing a pending command ID) or context about what happens after denial. The agent must infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute a shell command on the current platform
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | The command to execute | |
| args | No | Command arguments |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action but lacks critical details such as security implications, permission requirements, whether it's destructive, rate limits, or output format. This is a significant gap for a tool that executes shell commands, which can have high-risk behaviors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It's front-loaded and appropriately sized for its purpose, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of executing shell commands (potentially high-risk with no annotations) and lack of output schema, the description is incomplete. It fails to address security, permissions, or return values, leaving the agent with insufficient context for safe and effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with clear documentation for 'command' and 'args'. The description doesn't add any parameter-specific details beyond what the schema provides, such as examples or constraints, so it meets the baseline for high schema coverage without extra value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Execute') and resource ('a shell command on the current platform'), making the purpose understandable. However, it doesn't distinguish this tool from its siblings like 'approve_command' or 'deny_command', which appear to be related to command management but have different functions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. Given siblings like 'approve_command' and 'deny_command', it's unclear if 'execute_command' requires approval, operates independently, or has specific prerequisites, leaving the agent without usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the list of commands pending approval
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states this is a read operation ('Get'), implying it's non-destructive, but doesn't cover other aspects like permissions needed, rate limits, response format, or whether it returns all pending commands or a filtered subset. The description is minimal and lacks behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no wasted words. It's front-loaded with the core purpose and efficiently communicates the tool's function without unnecessary elaboration, making it easy for an agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no annotations, no output schema, and a simple input schema with no parameters, the description is minimal. While it states the purpose, it lacks context about what 'pending approval' means, how commands are structured, or what the return value looks like. For a tool in a security/command approval context, more completeness would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters with 100% schema description coverage, so no parameter documentation is needed. The description doesn't add parameter details, which is appropriate here. A baseline score of 4 is given since the schema fully covers the absence of parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and resource ('list of commands pending approval'), making the purpose immediately understandable. It doesn't explicitly distinguish from sibling tools like 'approve_command' or 'deny_command', but the verb 'Get' implies a read operation rather than an action on the commands themselves.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 like 'get_whitelist' or 'execute_command'. It doesn't mention prerequisites, context for pending commands, or any exclusions, leaving the agent to infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get information about the current platform and shell
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves information, implying a read-only operation, but doesn't specify what information is returned (e.g., OS version, shell type, environment details), whether it requires permissions, or if there are rate limits. This leaves significant gaps for a tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded with the core action ('Get information'), making it easy to parse, and every part of the sentence contributes to understanding the tool's function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete for a tool that retrieves system information. It doesn't explain what specific data is returned (e.g., platform details, shell version) or the format of the output, which is critical for an agent to use the tool effectively. This leaves too much ambiguity for practical use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters, and the schema description coverage is 100%, so there are no parameters to document. The description doesn't need to add parameter semantics, and it appropriately doesn't mention any. A baseline of 4 is applied as per the rules for tools with no parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('Get') and resource ('information about the current platform and shell'), making it immediately understandable. However, it doesn't explicitly differentiate this tool from its siblings (like 'execute_command' or 'get_pending_commands'), which focus on command execution and management rather than platform metadata.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. It doesn't mention prerequisites, context (e.g., use for system diagnostics or compatibility checks), or exclusions, leaving the agent to infer usage based on the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the list of whitelisted commands
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states 'Get the list' which implies a read-only operation, but doesn't specify whether this requires authentication, returns paginated results, includes metadata, or has rate limits. For a tool with zero annotation coverage, this leaves significant behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no wasted words. It's front-loaded with the core purpose ('Get the list of whitelisted commands') and doesn't include unnecessary elaboration. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters and no output schema, the description is minimally adequate but lacks context about the return format (e.g., structure of the whitelist, data types) and behavioral traits. It meets the basic requirement for a simple read operation but doesn't provide enough information for confident use without additional context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters with 100% schema description coverage, so the schema fully documents the absence of inputs. The description doesn't need to add parameter details, and it appropriately doesn't mention any. Baseline 4 is correct for zero-parameter tools where the schema already covers everything.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and the resource ('list of whitelisted commands'), making the purpose immediately understandable. It doesn't explicitly differentiate from siblings like 'get_pending_commands' or 'add_to_whitelist', but the verb+resource combination is specific enough to infer basic distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. It doesn't mention prerequisites, timing, or contrast with sibling tools like 'get_pending_commands' (which might retrieve unapproved commands) or 'add_to_whitelist' (which modifies the list). Usage is implied by the name but not explicitly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Remove a command from the whitelist
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | The command to remove from whitelist |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states the tool performs a removal action, implying mutation, but doesn't describe permissions needed, whether the change is reversible, error conditions, or what happens if the command isn't in the whitelist. This leaves significant gaps for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that states the core function without any wasted words. It's appropriately sized for a simple tool with one parameter and gets straight to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description is insufficient. It doesn't explain what happens after removal (e.g., confirmation message, error responses), doesn't mention security implications, and provides no context about the whitelist system it operates within.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 the single 'command' parameter adequately. The description doesn't add any additional meaning about parameter format, constraints, or examples beyond what the schema provides, meeting the baseline for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('remove') and target resource ('a command from the whitelist'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'deny_command' or 'update_security_level' which might have overlapping security functions, preventing a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 like 'deny_command' or 'update_security_level'. The description only states what it does, not when it's appropriate or what prerequisites might exist (e.g., whether the command must already be whitelisted).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update the security level of a whitelisted command
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | The command to update | |
| securityLevel | Yes | New security level for the command |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. While 'Update' implies a mutation, it doesn't specify required permissions, whether changes are reversible, error conditions (e.g., if command isn't whitelisted), or side effects. This leaves significant gaps for a security-related mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, direct sentence with zero wasted words. It front-loads the core action and target efficiently, making it easy to parse while conveying essential purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description is insufficient. It lacks critical context: what 'security level' means operationally, how changes affect command execution, error handling, or response format. Given the security-sensitive nature and sibling tools, more completeness is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so parameters are fully documented in the schema. The description adds no additional parameter context beyond implying 'command' refers to a whitelisted one. This meets the baseline for high schema coverage but doesn't enhance understanding of parameter usage or constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Update') and the target ('security level of a whitelisted command'), making the purpose immediately understandable. However, it doesn't explicitly differentiate this tool from siblings like 'add_to_whitelist' or 'remove_from_whitelist', which also modify command permissions but in different ways.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. It doesn't mention prerequisites (e.g., the command must already be whitelisted), contrast with 'approve_command'/'deny_command' for pending requests, or explain when changing security levels is appropriate versus adding/removing from the whitelist.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
add_to_whitelistapprove_commanddeny_commandexecute_commandget_pending_commandsget_platform_infoget_whitelistremove_from_whitelistupdate_security_levelScored across 9 tools
Each tool has a clearly distinct purpose with no ambiguity. For example, add_to_whitelist and remove_from_whitelist handle whitelist modifications, while approve_command and deny_command manage pending commands, and execute_command performs command execution. The descriptions reinforce these distinct roles, making misselection unlikely.
All tool names follow a consistent verb_noun pattern using snake_case, such as add_to_whitelist, get_pending_commands, and update_security_level. This predictability aids agent understanding and navigation without any deviations or mixed conventions.
With 9 tools, the count is well-scoped for a shell security management server. Each tool serves a clear purpose in the workflow, from command execution and approval to whitelist and platform management, avoiding bloat or thin coverage.
The tool set provides complete coverage for shell command security management, including CRUD operations for the whitelist (add, get, remove, update), a full lifecycle for pending commands (get, approve, deny), and core utilities like execute_command and get_platform_info. No obvious gaps exist for the domain.
MCP server for mandates, delegation, policy-gated execution, credential grants, and audit.
The MCP server for Azure DevOps, bringing the power of Azure DevOps directly to your agents.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
The MCP server that vets MCP servers: identity, risk grade and per-tool risk before you install.