A
securityF
licenseA
qualityA Model Context Protocol server implementation that enables secure remote command execution via SSH, with features for managing and using SSH credentials.
Last updated -
5
1
9
The Shell MCP Server enables secure shell command execution for AI models in a controlled environment.
Execute shell commands safely using the
run_commandtoolIntegrate with Claude Desktop and other MCP-compliant applications
Enforce security through command blacklisting (blocking dangerous commands like
rm,sudo,format)Validate command existence before execution
Handle errors gracefully with clear error messages
Communicate over standard I/O between processes
Implemented as a Node.js application that follows the Model Context Protocol, offering command validation and secure shell command execution.
Provides secure execution of shell commands with protective measures against dangerous operations including file system destruction, permission changes, and privilege escalation.
Shell MCP Server
A Node.js implementation of the Model Context Protocol (MCP) that provides secure shell command execution capabilities. This server allows AI models to execute shell commands in a controlled environment with built-in security measures. Easily integrates with Claude Desktop for connecting Claude with your shell.
Features
- MCP-compliant server implementation
- Secure command execution with blacklist protection
- Command existence validation
- Standard I/O based transport
- Error handling and graceful shutdown
Installation
Run npx mcp-shell.
To add it to Claude Desktop, run npx mcp-shell config. Or add npx -y mcp-shell to your config manually.
Start (or restart) Claude Desktop and you should see the MCP tool listed on the landing page.
Security Features
The server implements several security measures:
- Command Blacklisting
- Prevents execution of dangerous system commands
- Blocks access to critical system modifications
- Protects against file system destruction
- Prevents privilege escalation
- Command Validation
- Verifies command existence before execution
- Validates against the blacklist
- Returns clear error messages for invalid commands
Available Tools
The server provides one tool:
run_command
Executes a shell command and returns its output.
Input Schema:
Response:
- Success: Command output as plain text
- Error: Error message as plain text
Blacklisted Commands
The following command categories are blocked for security:
- File System Destruction Commands (rm, rmdir, del)
- Disk/Filesystem Commands (format, mkfs, dd)
- Permission/Ownership Commands (chmod, chown)
- Privilege Escalation Commands (sudo, su)
- Code Execution Commands (exec, eval)
- System Communication Commands (write, wall)
- System Control Commands (shutdown, reboot, init)
Error Handling
The server includes comprehensive error handling:
- Command not found errors
- Blacklisted command errors
- Execution errors
- MCP protocol errors
- Graceful shutdown on SIGINT
Implementation Details
The server is built using:
- Model Context Protocol SDK
- StdioServerTransport for communication
- execa for command execution
- command-exists for command validation
Development
To modify the security settings, you can:
- Edit the
BLACKLISTED_COMMANDSset to adjust blocked commands - Modify the
validateCommandfunction to add additional validation rules - Enhance the command parsing logic in the
CallToolRequestSchemahandler
local-only server
The server can only run on the client's local machine because it depends on local resources.
Tools
A Node.js implementation of the Model Context Protocol that provides secure shell command execution capabilities, allowing AI models like Claude to run shell commands in a controlled environment with built-in security measures.
- Features
- Installation
- Security Features
- Available Tools
- Blacklisted Commands
- Error Handling
- Implementation Details
- Development
Related Resources
Related MCP Servers
- -securityFlicense-qualityA TypeScript application that allows Claude to safely execute bash commands with security safeguards, providing a secure interface through the Model Context Protocol.Last updated -
- AsecurityAlicenseAqualityA secure Model Context Protocol server that allows AI models to safely interact with Windows command-line functionality, enabling controlled execution of system commands, project creation, and system information retrieval.Last updated -86MIT License
- -securityFlicense-qualityA secure interface that enables language models to execute shell commands on the host operating system through the Model Context Protocol.Last updated -1