sonirico/mcp-shell

Give hands to AI. MCP server to run shell commands securely, auditably, and on demand.

51
/ 100
Established

This project allows developers to connect an AI agent to a controlled shell environment, enabling the AI to execute specific commands on a server. It takes commands from an AI tool and returns the execution results, while providing security configurations to limit what the AI can do. This is designed for AI developers or system administrators who integrate AI agents into their workflows and need to manage their interaction with the underlying system securely.

Use this if you are building an AI agent and need it to safely run a predefined set of shell commands on a remote system, with auditing and strict security controls.

Not ideal if you need a full, unrestricted shell environment for your AI, or if you are not working with AI agents that require command execution capabilities.

AI-agent-development AI-security system-automation LLM-tooling server-administration
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 18 / 25

How are scores calculated?

Stars

63

Forks

16

Language

Go

License

GPL-3.0

Last pushed

Mar 10, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/sonirico/mcp-shell"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.