MCPShell
Provides a secure bridge between language models and operating system commands through a configurable YAML interface with constrai
MCPShell provides a secure bridge between LLMs and operating system commands through a configurable YAML-based interface. Developed by Alvaro, it features constraint-based security using CEL expressions to validate parameters before execution, multiple sandboxing options (including macOS sandbox-exec and Linux firejail), template-based command generation, and robust error handling. The implementation supports both direct command execution and server mode, making it particularly valuable for scenarios where AI assistants need controlled access to system utilities, diagnostics tools, or administrative functions without compromising security.
Source
Repository: https://github.com/inercia/mcpshell
Maintain MCPShell?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[MCPShell on getagentictools](https://getagentictools.com/mcp/inercia-mcpshell?ref=badge) Related mcp
OPNsense Provides Infrastructure as Code capabilities for OPNsense firewalls with declarative management of VLANs, firewall rules, DHCP con
RedTeam Toolkit Wraps 15+ offensive security tools including gogo, fscan, httpx, nuclei, and Impacket for AI-driven penetration testing, Active Di
OWASP ZAP Exposes OWASP ZAP web security scanning capabilities to AI agents via MCP for guided security assessments.
Context Optimizer Provides targeted file content extraction, secure terminal command execution with intelligent output analysis, and web research ca
GitHits Search public open-source code, documentation, metadata, vulnerabilities, changelogs, and examples.
Filesystem Provides secure, token-efficient access to local filesystems with advanced capabilities including line-targeted reading/editing, p